Bezahlte Endpunkte für autonome Agenten. Abrechnung über x402 in USDC auf Base Mainnet.
POST /v1/image-palette
Takes an image by URL or inline base64 and returns its colour palette: up to sixteen colours, each with the share of the visible area it covers, its HEX and sRGB values, its OKLCH coordinates, and the WCAG 2.1 contrast ratio against white, against black and against every other colour in the palette. The grouping runs in OKLab rather than RGB, because distance in RGB does not match what an eye sees — it merges dark blue with black and splits two yellows nobody tells apart.
0.002 USDC je Aufruf · MCP image_palette
POST /v1/stt
Takes an audio or video file by URL or inline base64 and returns the transcript: the full text, every word with start and end time and its own confidence, the utterances and paragraphs the recogniser separated, and the detected language with its confidence where no language was specified.
0.02 USDC je Aufruf · MCP stt
POST /v1/diarize
Takes an audio or video file by URL or inline base64 and reports who spoke when. Every turn comes back with its speaker label, start and end time, duration, word count and text, and consecutive words from the same speaker are merged into one turn rather than left as a word list.
0.025 USDC je Aufruf · MCP diarize
POST /v1/doc-translate
Takes a document as text, a public URL or inline base64 — PDF, DOCX, ODT, HTML and Markdown are read — and returns it translated into the target language. Structure is the point: heading levels, indentation, blank lines, list markers, the number of table columns, placeholders such as double-brace tokens or printf specifiers, URLs, e-mail addresses, file names and fenced code blocks are meant to come through untouched. Rather than assert that, the endpoint measures it.
0.006 USDC je Aufruf · MCP doc_translate
POST /v1/tts
Takes a text and returns it spoken, as MP3, WAV, Opus, FLAC or raw linear16, encoded base64 with its media type and the resulting running time. The voice is chosen freely from the provider catalogue — over a hundred voices across languages and accents — and is validated against that catalogue before the request goes out, so a mistyped voice name comes back immediately with a list of near matches instead of a provider error.
0.080 USDC je Aufruf · MCP tts
POST /v1/bg-remove
Takes an image by URL or inline base64 and returns it with the background removed, as PNG or WebP with a real alpha channel, together with the share of the frame that survived, the bounding box of the remaining subject and the option to crop to it.
0.01 USDC je Aufruf · MCP bg_remove
POST /v1/doc-convert
Takes one file, by URL or inline base64, and returns it in the format you ask for. Text documents go through pandoc, so DOCX, ODT, EPUB, HTML, Markdown, RST, Org, LaTeX, RTF, MediaWiki, Textile, CSV and Jupyter notebooks convert in both directions.
0.005 USDC je Aufruf · MCP doc_convert
POST /v1/doc-diff
Takes two documents, by URL, inline base64 or raw text, extracts the text of each and compares them. Paragraphs are the unit: the answer lists every block that was removed, added, or kept but reworded, and for reworded blocks it names the individual words that went and came, so a single changed number in a long clause is visible instead of the whole clause being flagged. Alongside the content diff a structural comparison reports headings, paragraph, list and table-line counts on both sides.
0.002 USDC je Aufruf · MCP doc_diff
POST /v1/pdf-fill
Called without "fields" it inspects: every AcroForm field of the PDF comes back with its name, type, current value, whether it is required or read-only, the permitted options for dropdowns, radio groups and list boxes, and the character limit of text fields. Called with "fields" it fills exactly those and returns the resulting PDF as base64, together with what each field held before and after.
0.005 USDC je Aufruf · MCP pdf_fill
POST /v1/image-dupe
Takes between two and eight images by URL or inline base64 and compares each pair. Three perceptual hashes are computed, because each fails differently: an average hash over an 8x8 grey image is cheap but moves with brightness, a gradient hash reads the slope between neighbouring pixels and survives exposure changes, and a DCT hash over the low frequencies of a 32x32 grey image is the sturdiest against rescaling and re-encoding.
0.005 USDC je Aufruf · MCP image_dupe
POST /v1/c2pa-verify
Takes one media file by URL or inline base64 and reads its C2PA manifest store.
0.002 USDC je Aufruf · MCP c2pa_verify
POST /v1/keyframes
Takes a video by URL or inline base64 and reports where the picture changes. FFmpeg measures the difference between consecutive frames; every jump above the threshold starts a new scene, and the answer lists each scene with start, end, duration and the fraction of the running time it covers, plus the raw detection score positions.
0.01 USDC je Aufruf · MCP keyframes
POST /v1/stt-batch
Takes 2 to 15 recordings by URL or inline base64, each with its declared length, and returns one transcript per file in the order given: full text, detected language, paragraphs, utterances, a confidence summary naming the weakest words with timestamps, and optionally every word with its timing. Billing is per started audio minute across the whole batch, at 0.017 USDC instead of the 0.02 USDC of a single /v1/stt call, at most 60 minutes per call. Every file is fetched and measured locally with ffprobe before anything is sent to the recogniser; if any file is longer than declared or is not audio, the whole batch is refused with the real lengths and nothing is charged. If a recognition fails after that, the call fails without settlement — there is no partial billing. Processing is by Deepgram with the per-request training opt-out on every file. Nothing is cached or stored.
0.017 USDC je Aufruf · MCP stt_batch
POST /v1/stt-translate
Takes an audio or video file by URL or inline base64 and returns subtitles in the target language with the timing of the original speech. The recording is transcribed with word timestamps, split into subtitle cues at pauses, six seconds or 84 characters, and every cue is translated on its own so that the number and timing of cues stay identical — this is checked on every model answer and a mismatch is retried once and otherwise refused without charge. The answer carries each cue with start, end, original text and translation, the full transcript, the full translation, and SRT and WebVTT files for both the target language and the original. Proper names, numbers and units are kept. Transcription is by Deepgram with the training opt-out on every request; translation is by a language model at Groq, which does not train on inputs; both processors are disclosed in every answer. The translation is machine-made and unreviewed. Billing per started audio minute; a recording longer than declared is refused with its real length and nothing is charged.
0.035 USDC je Aufruf · MCP stt_translate
POST /v1/audio-redact
Takes an audio or video file and returns a new audio file in which sensitive spoken content is covered by a 1 kHz tone or by silence. The recording is transcribed with word timestamps; then fixed, checkable patterns are searched in the words — e-mail addresses, also in spoken form, phone numbers of 7 to 15 digits, IBANs, card numbers that pass the Luhn check, and optionally any number of four or more digits — together with the names and terms you pass in terms, matched word by word regardless of case and punctuation. Names are not guessed: what is not in a pattern or in your list is not redacted, and the answer says so. Each hit is widened by a margin you choose, overlapping windows are merged, and the windows are cut into the audio with ffmpeg. The response carries the file inline as base64 (Opus, MP3, WAV or FLAC, at most 8 MB), the list of windows with category and a masked form of the hit, and the transcript with every redacted word replaced. Transcription is by Deepgram with the training opt-out; the audio processing runs locally. Billing per started audio minute; nothing is cached or stored.
0.03 USDC je Aufruf · MCP audio_redact
POST /v1/forced-align
Takes an audio or video file and the text spoken in it, and returns your text with timings: every word with start and end, every line with start and end, and ready SRT, WebVTT and LRC (karaoke/lyrics) files built from your own lines, so your spelling, punctuation and line breaks are kept. The recording is transcribed with word timestamps and your words are laid onto the recognised words by global sequence alignment. Each word is marked matched, substituted (heard differently at that position, time taken from there) or interpolated (not heard, time spread between its neighbours), and the shares are reported — if many words are interpolated, the text and the recording do not match, and the answer says so instead of returning confident-looking times. Text up to 60,000 characters, recording up to 30 minutes. Transcription is by Deepgram with the training opt-out; alignment runs locally. Billing per started audio minute; nothing is cached or stored.
0.025 USDC je Aufruf · MCP forced_align
POST /v1/voice-clean
Takes an audio or video file and returns a cleaned speech recording. A high-pass filter removes rumble and mains hum, an FFT noise reducer with continuous noise tracking lowers steady background noise such as fans, air conditioning and hiss by 10, 18 or 28 dB, a declicker removes short clicks, and the result is normalised to the target loudness in two passes. Noise floor, RMS level and integrated loudness are measured on the input and again on the output and returned, so the improvement is a measurement and not a promise. The file comes back inline as base64 in Opus, MP3, WAV or FLAC (at most 8 MB). Everything runs locally with ffmpeg; the audio does not leave this machine. Not provided, and stated in every answer: separating speech from music, removing reverb, or untangling overlapping speakers — that needs a neural separation model. Running time is kept, so transcript and subtitle timings from the original still fit. Billing per started audio minute; a longer file than declared is refused and nothing is charged.
0.004 USDC je Aufruf · MCP voice_clean
POST /v1/video-digest
Takes a video by URL or inline base64 and returns what an agent needs to work with it without watching it. The soundtrack is transcribed with paragraphs and timestamps; scene changes are detected with ffmpeg; chapters are cut at paragraph starts, preferring those within three seconds of a visual cut, at least min_chapter_seconds apart and at most 20. Per chapter the answer gives start, end, the spoken text, a title of up to eight words and a one-sentence summary, and optionally a JPEG thumbnail taken shortly after the chapter start. On top come a two-to-three-sentence summary of the whole video and YouTube chapter marks starting at 0:00. Chapter boundaries, timings and texts come from the recogniser and ffmpeg; only titles and summaries are written by a language model, which is checked for the right number of chapters and told to use nothing but the transcript. Transcription is by Deepgram with the training opt-out, titles by Groq, which does not train on inputs. Videos without speech are refused without charge. Billing per started minute of video.
0.04 USDC je Aufruf · MCP video_digest
POST /v1/stt-long
Takes a public URL of an audio or video file of up to 120 minutes and 150 MB and returns the transcript: full text, paragraphs with sentences and timings, utterances, the detected language, and a confidence breakdown naming the weakest words with timestamps; every word with its timing on request. The file is downloaded and its running time measured locally with ffprobe before anything is sent, so a recording longer than declared is refused with its real length and nothing is charged. Billing is per started audio minute at 0.018 USDC, below the 0.02 USDC of /v1/stt. Processing is by Deepgram with the per-request training opt-out. Words are off by default because two hours of word timings is several megabytes; switch include_words on when you need them. Nothing is cached or stored. The source must answer within 45 seconds.
0.018 USDC je Aufruf · MCP stt_long
POST /v1/meeting-minutes
Takes a meeting, call or interview recording and returns structured minutes. The audio is transcribed with speaker separation (S1, S2, ...); a language model then extracts the summary, topics, decisions, action items with the responsible person and deadline as they were spoken, and open questions. Every decision, task and question must carry a verbatim quote, and each quote is searched in the transcript: found quotes are marked verified with their timestamp, quotes that cannot be found are kept but marked verified:false — so invented items are visible, not hidden. Names appear only where they were said. Minutes language is selectable. Transcription by Deepgram with training opt-out, extraction by Groq, which does not train on inputs; both disclosed in every answer. Billing per started audio minute; a longer file than declared is refused and nothing is charged.
0.04 USDC je Aufruf · MCP meeting_minutes
POST /v1/podcast-shownotes
Takes a podcast episode of up to 120 minutes by URL or inline and returns publish-ready show notes: a title suggestion, a two-to-four-sentence description, chapters with timestamps (as text block for podcast players and YouTube), the people, organisations, products and links mentioned, up to five quotable sentences and keywords, plus the paragraphed transcript. Chapter boundaries are chosen by a language model as paragraph numbers only; their timestamps come from the recogniser. Every quote is searched in the transcript and dropped if it is not verbatim. Only what is said is listed as mentioned. Transcription by Deepgram with training opt-out, writing by Groq, which does not train on inputs. Billing per started audio minute; a longer file than declared is refused and nothing is charged.
0.035 USDC je Aufruf · MCP podcast_shownotes
POST /v1/dub
Takes an audio or video file of up to 10 minutes and returns a dubbed audio track in the target language. The speech is transcribed with timestamps and split into blocks; each block is translated on its own and spoken by a Deepgram voice of the target language, then placed at the start time of the original block. A spoken block that is longer than its slot is sped up to at most 1.6x, and any remaining overhang is reported per block. The original can keep running quietly underneath (original_volume) so that music and ambience stay. Returned are the audio file inline (Opus, MP3, WAV or FLAC, max 8 MB), the block list with original, translation, timing and tempo, and SRT subtitles of the translation. No voice cloning: the voice is a stock synthetic voice, chosen automatically or by name. Transcription and speech by Deepgram with training opt-out, translation by Groq; all disclosed. Billing per started audio minute.
0.1 USDC je Aufruf · MCP dub
POST /v1/clip-finder
Takes an audio or video file of up to 60 minutes and returns the best short clips: segments that stand on their own with a clear opening and a complete thought, between min_seconds and max_seconds long. A language model picks the segments as sentence numbers only; start and end times come from the recogniser and lengths are checked here, so a clip never starts or ends mid-sentence. Each clip carries title, hook line, reason, the spoken text, and an ffmpeg command that cuts it from the original. With render_audio the clips also come back as MP3 files inline (total max 8 MB). Transcription by Deepgram with training opt-out, selection by Groq, which does not train on inputs. Billing per started minute.
0.03 USDC je Aufruf · MCP clip_finder
POST /v1/filler-cut
Takes an audio or video file of up to 60 minutes and returns an edited audio file without filler words and with long pauses shortened. Speech is recognised with filler-word detection; every uh, um, er, äh, ähm, hm and similar is cut at its word boundaries, and every pause longer than max_pause_seconds is shortened to keep_pause_seconds rather than removed, so the speech keeps its rhythm. Returned are the file inline (Opus, MP3, WAV or FLAC, max 8 MB), the number of fillers and pauses removed, seconds saved, the cleaned transcript, and an edit list of removed intervals with the cumulative shift — enough to move transcript, subtitle or chapter times onto the new file. Filler detection is strongest in English; in other languages it depends on the recogniser transcribing the sounds at all, and the answer reports how many were found. Transcription by Deepgram with training opt-out, cutting locally with ffmpeg. Billing per started audio minute.
0.02 USDC je Aufruf · MCP filler_cut
POST /v1/burn-subtitles
Takes a video of up to 3 minutes and returns an MP4 with the subtitles rendered into the picture. Subtitles come either from you as SRT or WebVTT text, or, with transcribe=true, from the soundtrack (Deepgram, training opt-out) at 0.03 instead of 0.01 USDC per minute — the price is fixed before payment. Rendering runs locally with ffmpeg and libass in DejaVu Sans with outline, at the size and position you choose; the video is re-encoded to H.264/AAC and scaled to at most max_width so the file fits into the response (max 24 MB, inline base64). Returned are the video, the subtitles used as SRT, and the encoding facts. Billing per started minute of video; a longer video than declared is refused and nothing is charged.
0.01 USDC je Aufruf · MCP burn_subtitles
POST /v1/reading-check
Takes a recording and the text that was supposed to be read, and returns a reading assessment. The recording is transcribed with word timestamps and aligned to the text by global sequence alignment, ignoring case and punctuation. Every text word is marked correct, substituted (with what was heard), or omitted; words spoken but not in the text are listed as insertions. From this come accuracy, words correct per minute (WCPM, the standard reading-fluency measure), reading time, and hesitations — pauses longer than pause_seconds inside the reading, with the word after which they happened. Words read correctly but with low recogniser confidence are listed as worth listening to. This is not a phoneme-level pronunciation assessment, and the answer says so; a recogniser also tends to normalise what it hears, so a slight mispronunciation can still count as correct. Transcription by Deepgram with training opt-out. Billing per started audio minute.
0.025 USDC je Aufruf · MCP reading_check
POST /v1/call-analytics
Takes a recorded call or conversation of up to 60 minutes and returns conversation metrics computed from word timings and speaker separation: talk time and share per speaker, words per minute, number of turns, interruptions (a speaker starting while the other is still speaking or within 0.2 s), total and longest silence, longest monologue. Required phrases you pass are searched word by word and reported as found or missing with time and speaker; forbidden phrases likewise. A language model adds the caller concern, the outcome, sentiment per speaker, complaints and next steps; every complaint carries a quote that is checked against the transcript. Transcription by Deepgram with training opt-out, assessment by Groq, which does not train on inputs. Recording consent is the caller's responsibility. Billing per started audio minute.
0.04 USDC je Aufruf · MCP call_analytics
POST /v1/audio-search
Takes 1 to 15 recordings, each with its declared length (together at most 60 minutes), and up to 25 search terms or phrases. All files are transcribed with word timestamps, then every term is searched word by word, ignoring case and punctuation. Each hit carries the file, start and end time and eight words of context on either side. Single search words of five letters or more also match spellings with one differing letter, marked fuzzy, because that is exactly where the recogniser may have misheard. Returned per term are total hits and the files with hits; transcripts are included on request. Every file is fetched and measured locally before transcription, so a file longer than declared refuses the whole call without charge. Transcription by Deepgram with training opt-out. Billing per started minute across all files.
0.02 USDC je Aufruf · MCP audio_search
POST /v1/audiobook
Takes a text such as a chapter, article or report of up to 20,000 characters and returns it read aloud as one audio file. Lines starting with "# " become chapters; blank lines separate paragraphs, and long paragraphs are split at sentence boundaries. Every paragraph is spoken separately by a Deepgram voice of the chosen language (English, German, Spanish, French, Italian, Dutch or Japanese; automatic or by name), measured, and joined with pauses you set between paragraphs and chapters. Returned are the file inline (Opus or MP3, max 8 MB — about 20,000 characters fit as Opus), chapter marks with start times as text for players, and every paragraph with start, end and its text, enough for read-along highlighting per paragraph. Billing per started 1,000 characters at 0.07 USDC, fixed by the text length before payment. Speech by Deepgram, which receives only the text, with training opt-out. Synthetic voice; publishing it as a human narration is not permitted.
0.07 USDC je Aufruf · MCP audiobook
POST /v1/subtitles-multi
Takes an audio or video file and up to five target languages and returns subtitles for each: the speech is transcribed once with word timestamps, split into cues at pauses, six seconds or 84 characters, and every cue is translated on its own into each language in parallel. The number and timing of cues is identical across all languages and the original, and this is checked for every language. Returned per language: cue list with original and translation, SRT and WebVTT; plus the original SRT and WebVTT. Price: 0.02 USDC per minute plus 0.012 per target language, fixed before payment. Transcription by Deepgram with training opt-out, translation by Groq, which does not train on inputs. Machine translation, unreviewed.
0.032 USDC je Aufruf · MCP subtitles_multi
POST /v1/interview-article
Takes an interview recording of up to 60 minutes and returns an edited question-and-answer text ready for editing: title, two-to-three-sentence standfirst, and the questions with smoothed answers — fillers, false starts and repetitions removed, grammar fixed, statements, figures and names kept exactly. Speakers are separated automatically, and their labels can be replaced with names. Every answer must include a verbatim quote, and each quote is searched in the transcript and returned as verified with its timestamp, or marked unverified — so a smoothing that shifted meaning becomes visible. The raw speaker-separated transcript is included. Article language selectable. Transcription by Deepgram with training opt-out, editing by Groq, which does not train on inputs. Billing per started audio minute.
0.05 USDC je Aufruf · MCP interview_article
POST /v1/voice-note-tasks
Takes a voice note or memo of up to 10 minutes and returns its contents as separate entries: tasks with due date, events with start and end, contacts with spoken phone number or e-mail, and notes. Relative expressions such as "tomorrow", "next Tuesday" or "end of the month" are resolved against reference_time in the given IANA time zone, and every entry carries the verbatim phrase it was taken from, checked against the transcript. Events and dated tasks come additionally as an iCalendar file (VEVENT and VTODO) that Google Calendar, Outlook and Apple Calendar import directly. Phone numbers and addresses are only taken when they were spoken; nothing is invented. Transcription by Deepgram with training opt-out, structuring by Groq, which does not train on inputs. Billing per started audio minute.
0.03 USDC je Aufruf · MCP voice_note_tasks
POST /v1/lecture-flashcards
Takes a lecture or talk recording of up to 120 minutes and returns study material: a summary, key terms, flashcards with front and back, and multiple-choice questions with four options, the correct answer and an explanation. Every card and question names the paragraph of the transcript it comes from, and the timestamp of that paragraph is attached so learners can jump to the place in the recording. Questions whose source paragraph does not exist or whose correct answer index is invalid are dropped and counted. A CSV in front;back form imports directly into Anki and Quizlet. Number of cards and questions and the output language are selectable. Transcription by Deepgram with training opt-out, generation by Groq, which does not train on inputs. Billing per started audio minute.
0.04 USDC je Aufruf · MCP lecture_flashcards
POST /v1/speech-coach
Takes a recording of a talk, pitch, lesson or rehearsal of up to 30 minutes and returns delivery metrics computed from word timestamps: words per minute overall and for every minute, filler words (uh, um, äh, ähm) and hedge words (basically, actually, eigentlich, sozusagen) per minute with their most frequent forms, pauses over one second with position, average and longest sentences, and phrases of three or more words that recur. On top, a language model gives two to three strengths and three to five concrete tips, each tied to a stated metric or passage; it sees only the numbers and excerpts. Reference values: 130 to 160 words per minute is a common target for presentations. Transcription by Deepgram with filler-word detection and training opt-out, tips by Groq. Billing per started audio minute.
0.025 USDC je Aufruf · MCP speech_coach
POST /v1/ad-detect
Takes a podcast episode of up to 120 minutes and returns its advertising segments: paid sponsor reads, self-promotion (newsletter, Patreon, merchandise) and cross-promotion of other shows, each with start and end on sentence boundaries, the advertiser and any discount code as spoken, and a verbatim evidence phrase that is checked against the transcript — a segment without verified evidence is reported but never cut. Product mentions in the conversation itself are not counted as ads. With remove_ads the episode comes back without the selected kinds of segments as an audio file (Opus or MP3, max 8 MB) and an edit list to shift timestamps. Useful for ad-free versions, ad audits and sponsor reporting. Transcription by Deepgram with training opt-out, detection by Groq. Billing per started audio minute.
0.03 USDC je Aufruf · MCP ad_detect
POST /v1/sentiment-timeline
Takes a conversation, call, focus group or meeting of up to 60 minutes, separates speakers, splits it into time windows (default 60 seconds) and returns a sentiment timeline: per window and speaker a score from -1 to +1, a label such as tense, pleased or annoyed, and a verbatim quote that is checked against the transcript. Also returned are the average per speaker, the largest changes as turning points with time, and talk share per window computed from word timings. Scores are a language model's reading of what was said, not a measurement of emotion in the voice, and the answer says so. Transcription by Deepgram with speaker separation and training opt-out, scoring by Groq, which does not train on inputs. Billing per started audio minute.
0.035 USDC je Aufruf · MCP sentiment_timeline
POST /v1/podcast-mix
Takes 2 to 4 audio tracks of the same conversation, one per speaker (remote recordings or a multitrack recorder), of up to 20 minutes, and returns one mixed episode. Every track gets a high-pass filter against rumble and hum, light FFT noise reduction, a noise gate that closes while that speaker is silent so that bleed and room noise of the others do not sit twice in the mix, and is brought to a common loudness so nobody is too quiet; then the tracks are summed and the mix is brought to the target loudness. Loudness of each input track and of the final mix is measured and returned. Tracks must start at the same moment; offsets can be given per track in milliseconds. Returned as Opus, MP3, WAV or FLAC inline (max 8 MB). Runs locally with ffmpeg; nothing leaves this machine. Billing per started minute of the longest track times number of tracks.
0.012 USDC je Aufruf · MCP podcast_mix
POST /v1/numbers-extract
Takes a call, meeting, dictation or interview of up to 60 minutes and returns its numeric statements as structured data: kind (amount, percent, date, time, duration, quantity, phone, year), the wording as spoken, a normalised value, unit or currency, what the number refers to, the sentence it comes from and its timestamp. A language model classifies; each value must point to an existing sentence whose wording contains it, otherwise it is dropped and counted — so numbers are never invented. Transcription by Deepgram with smart formatting and training opt-out, classification by Groq. Billing per started audio minute.
0.025 USDC je Aufruf · MCP numbers_extract
POST /v1/entities
Takes a recording of up to 60 minutes and returns the named entities in it — people, places, organisations, products, events — each with its type, a short description taken from the context, and every mention with timestamp and surrounding words. A language model proposes the names; every name is then searched word by word in the transcript, and names without a match are dropped and counted. Useful for indexing archives, show notes, CRM notes and research. Transcription by Deepgram with training opt-out, naming by Groq. Billing per started audio minute.
0.025 USDC je Aufruf · MCP entities
POST /v1/audio-qa
Takes a recording of up to 60 minutes and up to ten questions, and answers each one strictly from the transcript. Every answer cites the sentence numbers it relies on; those sentences are returned with their text and timestamps, and citations to sentences that do not exist are removed. When the recording does not contain the answer, the question is marked not answered instead of guessed. Answer language selectable. Transcription by Deepgram with training opt-out, answering by Groq, which does not train on inputs. Billing per started audio minute regardless of the number of questions.
0.03 USDC je Aufruf · MCP audio_qa
POST /v1/msds-extract
Downloads one public PDF up to 5 MiB through SSRF-safe redirect checks or accepts extracted text, runs pdftotext in a private temporary directory, and deterministically extracts the requested codes with their source lines. Temporary PDF and text files are deleted before the response. It does not OCR scans, identify symbols from images, translate legal wording or certify regulatory completeness.
0.010 USDC je Aufruf · MCP msds_extract
POST /v1/quote-search
Takes a recording and a topic or question (for example "pricing", "the new law", "why they founded the company") and returns up to the requested number of verbatim, self-contained statements about it that work as quotes in an article, post or report, each with timestamp, speaker label if available, and a short note on what it says. Every finding carries a verbatim quote from the transcript; quotes are searched in the transcript and findings whose quote cannot be found are dropped and counted, so nothing invented passes through. Transcription by Deepgram with training opt-out, analysis by a language model at Groq, which does not train on inputs; both disclosed in every answer. Billing per started audio minute; a longer file than declared is refused and nothing is charged.
0.03 USDC je Aufruf · MCP quote_search
POST /v1/glossary
Takes a recording of up to 120 minutes and returns the specialist terms, abbreviations and jargon it uses, each with a short explanation based on how it is used in the recording (not a general dictionary definition), its category, the quote where it first appears and the timestamp. Every finding carries a verbatim quote from the transcript; quotes are searched in the transcript and findings whose quote cannot be found are dropped and counted, so nothing invented passes through. Transcription by Deepgram with training opt-out, analysis by a language model at Groq, which does not train on inputs; both disclosed in every answer. Billing per started audio minute; a longer file than declared is refused and nothing is charged.
0.03 USDC je Aufruf · MCP glossary
POST /v1/question-detect
Takes a conversation of up to 60 minutes — interview, meeting, sales or support call — and returns every question asked, detected from the recogniser's punctuation together with speaker separation, with speaker, timestamp and the reply that followed. Whether a question was taken up is measured: another speaker saying at least five words within 30 seconds counts as a reply. Optionally a language model rates each question as answered, partly answered, evaded or not answered, with a one-sentence reason. Counts per speaker show who asked and who answered. Transcription by Deepgram with speaker separation and training opt-out. Billing per started audio minute.
0.025 USDC je Aufruf · MCP question_detect
POST /v1/claims-extract
Takes a recording of up to 120 minutes and returns the statements in it that assert something checkable — statistics, dates, causal claims, comparisons, attributions — rewritten as a neutral claim, typed, and with a note on what source or data would settle it. Opinions, predictions and jokes are left out. It does not judge whether a claim is true; it prepares fact-checking. Every finding carries a verbatim quote from the transcript; quotes are searched in the transcript and findings whose quote cannot be found are dropped and counted, so nothing invented passes through. Transcription by Deepgram with training opt-out, analysis by a language model at Groq, which does not train on inputs; both disclosed in every answer. Billing per started audio minute; a longer file than declared is refused and nothing is charged.
0.035 USDC je Aufruf · MCP claims_extract
POST /v1/commitments
Takes a call or meeting of up to 60 minutes, separates the speakers and returns every commitment made: what was promised, by which speaker, the deadline or condition as spoken, its kind (delivery, price, refund, callback, guarantee, other), the quote and timestamp. Useful for sales and support follow-up, dispute evidence and compliance reviews. Every finding carries a verbatim quote from the transcript; quotes are searched in the transcript and findings whose quote cannot be found are dropped and counted, so nothing invented passes through. Transcription by Deepgram with training opt-out and speaker separation, analysis by a language model at Groq, which does not train on inputs; both disclosed in every answer. Billing per started audio minute; a longer file than declared is refused and nothing is charged.
0.035 USDC je Aufruf · MCP commitments
POST /v1/objections
Takes a sales call or demo of up to 60 minutes, separates the speakers and returns every objection raised: its category (price, timing, competitor, authority, need, trust, other), the speaker, the quote, a short summary of how it was answered, and whether it was resolved, partly resolved or left open. For sales coaching and win-loss analysis. Every finding carries a verbatim quote from the transcript; quotes are searched in the transcript and findings whose quote cannot be found are dropped and counted, so nothing invented passes through. Transcription by Deepgram with training opt-out and speaker separation, analysis by a language model at Groq, which does not train on inputs; both disclosed in every answer. Billing per started audio minute; a longer file than declared is refused and nothing is charged.
0.035 USDC je Aufruf · MCP objections
POST /v1/pii-report
Takes a recording of up to 60 minutes and returns a report of the personal data it contains: names, postal addresses, phone numbers, e-mail addresses, dates of birth, bank and card numbers, ID numbers, and special categories such as health information, each with category, a GDPR-oriented sensitivity rating (normal or special category), the quote and the timestamp. Nothing is redacted — use /v1/audio-redact for that. Helps decide whether a recording may be shared or must be redacted. Every finding carries a verbatim quote from the transcript; quotes are searched in the transcript and findings whose quote cannot be found are dropped and counted, so nothing invented passes through. Transcription by Deepgram with training opt-out, analysis by a language model at Groq, which does not train on inputs; both disclosed in every answer. Billing per started audio minute; a longer file than declared is refused and nothing is charged.
0.03 USDC je Aufruf · MCP pii_report
POST /v1/profanity-check
Takes a recording of up to 120 minutes and returns every instance of profanity, slurs, personal insults and explicit sexual or violent language, each with category, severity (mild, moderate, strong), the quote and timestamp, plus a summary for ad-suitability decisions. Context matters and is considered: quoting or discussing a word is marked as such. Every finding carries a verbatim quote from the transcript; quotes are searched in the transcript and findings whose quote cannot be found are dropped and counted, so nothing invented passes through. Transcription by Deepgram with training opt-out, analysis by a language model at Groq, which does not train on inputs; both disclosed in every answer. Billing per started audio minute; a longer file than declared is refused and nothing is charged.
0.025 USDC je Aufruf · MCP profanity_check
POST /v1/brand-mentions
Takes a recording of up to 120 minutes and a list of up to 30 brand, product or competitor names, and returns every mention of them — also in obvious variants and abbreviations — with the tone of the mention, a one-line context, whether it is a paid or sponsored mention, the quote and the timestamp, plus counts per name. Names not in the list are ignored. Every finding carries a verbatim quote from the transcript; quotes are searched in the transcript and findings whose quote cannot be found are dropped and counted, so nothing invented passes through. Transcription by Deepgram with training opt-out, analysis by a language model at Groq, which does not train on inputs; both disclosed in every answer. Billing per started audio minute; a longer file than declared is refused and nothing is charged.
0.03 USDC je Aufruf · MCP brand_mentions
POST /v1/faq-from-audio
Takes a recording of up to 60 minutes and derives FAQ entries from it: the questions that were actually asked (or clearly implied), rewritten as clean FAQ questions, with the answer as it was given in the recording, a topic tag, and the quote and timestamp where the answer is given. Questions that were asked but not answered are listed as open so the knowledge base can be completed. Every finding carries a verbatim quote from the transcript; quotes are searched in the transcript and findings whose quote cannot be found are dropped and counted, so nothing invented passes through. Transcription by Deepgram with training opt-out, analysis by a language model at Groq, which does not train on inputs; both disclosed in every answer. Billing per started audio minute; a longer file than declared is refused and nothing is charged.
0.03 USDC je Aufruf · MCP faq_from_audio
POST /v1/blog-from-audio
Takes a recording of up to 120 minutes and writes a blog article from it: headline, short intro, body in sections with subheadings, three to five key takeaways, a meta description of up to 155 characters and SEO keywords, as structured fields and as ready Markdown. Target length and tone (neutral, conversational, professional) are selectable. The model must back the key statements of the text with verbatim quotes; every quote is searched in the transcript and returned with its timestamp, and unverified quotes are counted, so it is checkable that the text only says what was said. Transcription by Deepgram with training opt-out, writing by a language model at Groq, which does not train on inputs; both disclosed. Output language selectable. Billing per started audio minute; a longer file than declared is refused and nothing is charged.
0.04 USDC je Aufruf · MCP blog_from_audio
POST /v1/social-posts
Takes a recording of up to 120 minutes and the platforms you want, and writes posts for each: a LinkedIn post, an X post or short thread, an Instagram caption, and so on, each within the platform length limit (checked and trimmed here), with fitting hashtags and a reference to the moment in the recording, for clip pairing. Several variants per platform are possible. The model must back the key statements of the text with verbatim quotes; every quote is searched in the transcript and returned with its timestamp, and unverified quotes are counted, so it is checkable that the text only says what was said. Transcription by Deepgram with training opt-out, writing by a language model at Groq, which does not train on inputs; both disclosed. Output language selectable. Billing per started audio minute; a longer file than declared is refused and nothing is charged.
0.035 USDC je Aufruf · MCP social_posts
POST /v1/press-release
Takes a recording of up to 90 minutes of a press conference, product announcement or keynote and writes a press release in the usual structure: headline, subheadline, lead paragraph with the who-what-when-where, body paragraphs, two to four quotes that are taken verbatim from the recording and attributed to the speaker as named or as a placeholder, and placeholders for boilerplate and press contact. Figures, dates and names exactly as spoken; nothing is added. The model must back the key statements of the text with verbatim quotes; every quote is searched in the transcript and returned with its timestamp, and unverified quotes are counted, so it is checkable that the text only says what was said. Transcription by Deepgram with training opt-out, writing by a language model at Groq, which does not train on inputs; both disclosed. Output language selectable. Billing per started audio minute; a longer file than declared is refused and nothing is charged.
0.04 USDC je Aufruf · MCP press_release
POST /v1/formal-minutes
Takes a recording of a formal meeting of up to 120 minutes and writes minutes in the structure such bodies use: meeting details as spoken (opening, quorum, chair), agenda items in order, for each the discussion in brief, motions with who moved them, votes with the result exactly as announced (for, against, abstentions), resolutions in their wording, and action points with owner and deadline. Results are only recorded as announced in the recording; if a count was not stated, it says so. The model must back the key statements of the text with verbatim quotes; every quote is searched in the transcript and returned with its timestamp, and unverified quotes are counted, so it is checkable that the text only says what was said. Transcription by Deepgram with training opt-out, writing by a language model at Groq, which does not train on inputs; both disclosed. Output language selectable. Billing per started audio minute; a longer file than declared is refused and nothing is charged.
0.045 USDC je Aufruf · MCP formal_minutes
POST /v1/howto-from-video
Takes a tutorial, product demo, repair or cooking video of up to 60 minutes and writes structured instructions from what is said: title, goal, what is needed (tools, materials, ingredients with quantities as spoken), numbered steps each with the timestamp where it starts in the video, warnings and tips. Steps are taken only from the narration; actions that are only shown and not said cannot be captured, and the answer says so. The model must back the key statements of the text with verbatim quotes; every quote is searched in the transcript and returned with its timestamp, and unverified quotes are counted, so it is checkable that the text only says what was said. Transcription by Deepgram with training opt-out, writing by a language model at Groq, which does not train on inputs; both disclosed. Output language selectable. Billing per started audio minute; a longer file than declared is refused and nothing is charged.
0.04 USDC je Aufruf · MCP howto_from_video
POST /v1/talk-notes
Takes a recording of up to 120 minutes and writes study notes: a title, the central theme in one sentence, an outline of main points and sub-points in the order they were made, every text reference, scripture passage, book or source cited exactly as spoken (nothing added from outside), key sentences, and three to six questions for reflection or group discussion. For congregations, study groups, students and listeners who want to follow up. The model must back the key statements of the text with verbatim quotes; every quote is searched in the transcript and returned with its timestamp, and unverified quotes are counted, so it is checkable that the text only says what was said. Transcription by Deepgram with training opt-out, writing by a language model at Groq, which does not train on inputs; both disclosed. Output language selectable. Billing per started audio minute; a longer file than declared is refused and nothing is charged.
0.035 USDC je Aufruf · MCP talk_notes
POST /v1/email-from-voice
Takes a voice note or dictation of up to 10 minutes ("write to Mr Weber that the offer is late and we will send it Friday...") and returns an e-mail draft: subject, salutation, body and closing, in formal or informal register and the chosen tone, with names, dates and figures exactly as spoken. Points the speaker left open are listed separately instead of being invented. Nothing is sent; the draft is returned as text and as an .eml-ready body. The model must back the key statements of the text with verbatim quotes; every quote is searched in the transcript and returned with its timestamp, and unverified quotes are counted, so it is checkable that the text only says what was said. Transcription by Deepgram with training opt-out, writing by a language model at Groq, which does not train on inputs; both disclosed. Output language selectable. Billing per started audio minute; a longer file than declared is refused and nothing is charged.
0.03 USDC je Aufruf · MCP email_from_voice
POST /v1/audio-convert
Takes an audio or video file and returns the audio in the requested format — MP3, Opus, Ogg Vorbis, AAC in M4A, WAV or FLAC — with selectable bitrate for lossy formats, sample rate and mono or stereo. Only the first audio stream is converted; the content is not altered otherwise. Input and output are measured with ffprobe and both are reported, including size change. Output inline as base64, max 8 MB. Runs entirely on this machine; nothing is sent to third parties or stored. Billing per started audio minute.
0.002 USDC je Aufruf · MCP audio_convert
POST /v1/audio-trim
Takes an audio or video file (up to 24 MB) and returns the part between start_seconds and end_seconds as an audio file. The cut is sample-accurate because the excerpt is re-encoded rather than cut at the nearest frame. Optional fade-in and fade-out in seconds. If the end lies beyond the file, the excerpt ends with the file and this is reported. Output inline as base64, max 8 MB. Runs locally with ffmpeg; nothing leaves this machine. Fixed price per call.
0.003 USDC je Aufruf · MCP audio_trim
POST /v1/audio-concat
Takes 2 to 10 audio or video files (each up to 24 MB, together up to 60 minutes) and joins their audio in the given order. Between parts either a pause of chosen length or a crossfade is placed; optionally every part is brought to a common loudness first so that no part is suddenly louder. The start time of every part in the joined file is measured and returned, ready for chapter marks. Output as MP3, Opus, WAV or FLAC inline, max 8 MB. Runs locally with ffmpeg; nothing leaves this machine. Billing per file.
0.004 USDC je Aufruf · MCP audio_concat
POST /v1/silence-split
Takes an audio or video file of up to 60 minutes, detects silences longer than min_silence_seconds below threshold_db and cuts the recording into parts at the middle of each silence. Parts shorter than min_part_seconds are merged with their neighbour; at most 50 parts. Returned are the cut list with start, end and duration of every part and, if they fit into 8 MB together, the parts themselves as MP3 inline; otherwise only the cut list, which is stated. Runs locally with ffmpeg; nothing leaves this machine. Billing per started audio minute.
0.003 USDC je Aufruf · MCP silence_split
POST /v1/chapter-split
Takes an audio or video file of up to 60 minutes and a list of chapters with start time and title (e.g. from podcast show notes or topic segmentation) and returns one audio file per chapter, from its start to the next chapter's start, cut exactly by re-encoding. Up to 50 chapters; if all files together exceed 8 MB, Opus at a lower bitrate is suggested. Each file carries its title and duration. Runs locally with ffmpeg; nothing leaves this machine. Billing per started audio minute.
0.003 USDC je Aufruf · MCP chapter_split
POST /v1/intro-outro
Takes a main recording and an intro and/or outro file and returns one episode: intro, main part, outro, joined with short crossfades, every part brought to the same loudness first and the result normalised to the target. The measured start of the main part in the new file is returned, because every chapter mark and transcript time of the original shifts by that amount. Output as MP3, Opus, WAV or FLAC inline, max 8 MB. Billing per started minute of the main recording. Runs locally with ffmpeg; only use jingles you have the rights to.
0.003 USDC je Aufruf · MCP intro_outro
POST /v1/music-ducking
Takes a voice recording and a music track and returns one mix in which the music is lowered by sidechain compression whenever the voice is present and returns in pauses — the standard podcast and voice-over sound. The music is looped or trimmed to the voice length, starts at the chosen bed level and fades out at the end; the voice is levelled first. Depth of ducking and music level are selectable, and the mix is brought to the target loudness, measured afterwards. Billing per started minute of the voice track. Only use music you have the rights to. Runs locally with ffmpeg.
0.004 USDC je Aufruf · MCP music_ducking
POST /v1/stereo-check
Takes an audio or video file of up to 60 minutes and measures each channel and the mono sum: RMS level per channel and channel balance, the correlation-like difference between left and right (identical channels mean the file is mono in a stereo container), a silent or much quieter channel, and the level loss of the mono sum compared with the stereo signal — a loss of more than about 3 dB means parts cancel out on phones, smart speakers and kitchen radios, typically from an inverted channel. Returns a verdict with the findings. Runs locally with ffmpeg. Billing per started audio minute.
0.002 USDC je Aufruf · MCP stereo_check
POST /v1/clipping-detect
Takes an audio or video file of up to 60 minutes and measures every 100 ms window for peak level and the number of samples sitting at the peak. Windows that reach the clipping threshold (default -0.1 dBFS) with several consecutive peak samples are merged into passages, each with start, end, duration and the number of clipped windows, sorted by severity. The verdict says clean, minor or severe, and the total clipped time is given. Clipping cannot be repaired here; this finds it so a take can be redone or a part replaced. Runs locally with ffmpeg; nothing leaves this machine. Billing per started audio minute.
0.003 USDC je Aufruf · MCP clipping_detect
POST /v1/hum-remove
Takes an audio or video file and removes electrical mains hum — the steady buzz at 50 Hz (Europe and most of the world) or 60 Hz (North America) and its harmonics — with narrow notch filters (Q 30) on the fundamental and up to eight harmonics, so speech and music outside those narrow bands stay untouched. Choose the mains frequency or leave it on 50 by default; the number of harmonics is selectable. Broadband noise, buzz from bad cables that is not on the mains frequency, and clicks are not removed. Runs locally with ffmpeg; nothing leaves this machine and nothing is stored. Output inline as base64, max 8 MB. Billing per started audio minute; a longer file than declared is refused and nothing is charged.
0.003 USDC je Aufruf · MCP hum_remove
POST /v1/de-ess
Takes a voice recording and reduces sibilance, the harsh hiss on s, sh, z and ch sounds that close microphones and bright voices produce, with ffmpeg's de-esser at light, medium or strong intensity. Only the sibilant frequencies are attenuated when they occur, so the rest of the voice keeps its brightness. Too strong a setting makes speech sound lispy; medium suits most podcasts. Runs locally with ffmpeg; nothing leaves this machine and nothing is stored. Output inline as base64, max 8 MB. Billing per started audio minute; a longer file than declared is refused and nothing is charged.
0.003 USDC je Aufruf · MCP de_ess
POST /v1/speed-change
Takes an audio or video file and changes its tempo by a factor from 0.5 (half speed) to 2.0 (double speed) while keeping the pitch, using the Rubber Band time-stretching library through ffmpeg — good for faster listening, language learning at reduced speed, or fitting a voice-over into a slot. The new running time is measured and returned. All timestamps of the original scale by 1/factor. Runs locally with ffmpeg; nothing leaves this machine and nothing is stored. Output inline as base64, max 8 MB. Billing per started audio minute; a longer file than declared is refused and nothing is charged.
0.003 USDC je Aufruf · MCP speed_change
POST /v1/pitch-shift
Takes an audio or video file and transposes it by a number of semitones from -12 to +12 while keeping tempo and running time, using the Rubber Band library through ffmpeg. With preserve_formants on, voices keep their natural timbre instead of sounding like cartoon characters — useful for practice tracks in another key or light voice anonymisation. Pitch-shifting is not a secure anonymisation: it can often be reversed, and the answer says so. Runs locally with ffmpeg; nothing leaves this machine and nothing is stored. Output inline as base64, max 8 MB. Billing per started audio minute; a longer file than declared is refused and nothing is charged.
0.003 USDC je Aufruf · MCP pitch_shift
POST /v1/waveform-image
Takes an audio or video file (up to 24 MB) and returns its waveform as a PNG image with chosen width, height, wave colour and background colour, mono or one lane per channel, optionally on a logarithmic scale that makes quiet speech visible. Rendered locally with ffmpeg; the image comes back inline as base64 along with duration and size. Nothing leaves this machine. Fixed price per call.
0.003 USDC je Aufruf · MCP waveform_image
POST /v1/spectrogram-image
Takes an audio or video file (up to 24 MB) and returns a spectrogram image: time on the horizontal axis, frequency on the vertical, intensity as colour, with scale and legend. It makes visible what the ear misses — mains hum as a line at 50 or 60 Hz, broadband noise, the cut-off of a phone or low-bitrate recording, and hard edits. Size, colour scheme and linear or logarithmic intensity are selectable. Rendered locally with ffmpeg; returned inline as PNG base64. Nothing leaves this machine. Fixed price per call.
0.003 USDC je Aufruf · MCP spectrogram_image
POST /v1/loudness-report
Takes 1 to 20 audio or video files (each up to 24 MB) and returns a loudness report: integrated loudness in LUFS, true peak in dBTP, loudness range in LU and duration per file, measured with ffmpeg's EBU R128 meter. Every file is rated against the selected targets — podcast -16 LUFS, streaming -14, EBU broadcast -23, ATSC broadcast -24, ACX audiobook -20 — with pass or fail and the gain in dB that would reach the target. Files that fail to decode are reported, not dropped. Runs locally; nothing leaves this machine. Billing per file.
0.002 USDC je Aufruf · MCP loudness_report
POST /v1/ringtone-cut
Takes an audio or video file and returns a ringtone: the part from start_seconds for length_seconds (at most 30, the iPhone limit), with a short fade-in and a fade-out, normalised to a loud but undistorted level, as M4R for iPhone or MP3 and Ogg for Android. Only use material you have the rights to. Runs locally with ffmpeg; nothing leaves this machine and nothing is stored. Output inline as base64, max 8 MB. Billing per started audio minute; a longer file than declared is refused and nothing is charged.
0.003 USDC je Aufruf · MCP ringtone_cut
POST /v1/tts-paced
Takes a text of up to 10,000 characters with simple markers: [pause N] inserts N seconds of silence (up to 30), and a blank line inserts the paragraph pause you set. Every text part is spoken by a natural synthetic voice in one of seven languages, and the parts and pauses are joined exactly, so a breathing exercise or a dictation gets the gaps it needs. Returned are the audio file (MP3, Opus or WAV) and the start and end of every spoken part and pause. Speech by Deepgram with training opt-out. Billing per started 1,000 characters of spoken text, fixed before payment.
0.07 USDC je Aufruf · MCP tts_paced
POST /v1/tts-dialogue
Takes a script of up to 200 lines (together up to 12,000 characters), each with a speaker role and text, and returns one audio file: every role gets its own voice — assigned automatically from the voices of the chosen language, or set per role — and lines are separated by a pause you choose. Returned with the file are the start and end time of every line and an SRT, so the dialogue can be shown along. Languages: English, German, Spanish, French, Italian, Dutch, Japanese. Speech by Deepgram with training opt-out. Billing per started 1,000 characters, fixed before payment from the script.
0.07 USDC je Aufruf · MCP tts_dialogue
POST /v1/phone-prompts
Takes up to 30 prompts, each with an id and its text (total up to 10,000 characters), and returns one audio file per prompt in telephone format: 8 kHz mono WAV in 16-bit PCM, G.711 A-law (Europe) or µ-law (North America), or MP3 for preview. Files are named after the ids so they can be dropped into a phone system. Short silence is added at start and end, as phone systems expect; the voice is selectable per language (English, German, Spanish, French, Italian, Dutch, Japanese). Speech by Deepgram with training opt-out. Billing per started 1,000 characters, fixed before payment from the text.
0.07 USDC je Aufruf · MCP phone_prompts
POST /v1/pronunciation-samples
Takes up to 100 words, names or short phrases in one of seven languages and returns one MP3 per item spoken by a natural synthetic voice, optionally a second version at 75 % speed (pitch kept) for learners, and a combined file with all items in order separated by pauses. File names follow the list position. Ready to attach to flashcards (Anki, Quizlet) or a glossary. Speech by Deepgram with training opt-out. Billing per started 1,000 characters (doubled with the slow version), fixed before payment.
0.07 USDC je Aufruf · MCP pronunciation_samples
POST /v1/video-convert
Takes a video of up to 10 minutes and 24 MB and returns it as MP4 with H.264 and AAC and fast-start for web playback, or as WebM with VP9 and Opus, scaled down to max_width if larger (aspect ratio kept), at high, medium or low quality, optionally with the audio removed. Input and output facts — container, codec, resolution, frame rate, duration and size — are measured and returned with the size ratio. Output inline as base64, max 24 MB. Runs locally with ffmpeg; nothing leaves this machine. Billing per started video minute.
0.008 USDC je Aufruf · MCP video_convert
POST /v1/video-trim
Takes a video (up to 24 MB) and returns the part between start_seconds and end_seconds, at most 180 seconds, as MP4 with H.264 and AAC. The clip is re-encoded, so it starts exactly at the requested time rather than at the previous keyframe. Optional maximum width and short video and audio fades at both ends. If the end lies beyond the video, the clip ends with the video and this is reported. Output inline as base64, max 24 MB. Runs locally with ffmpeg. Fixed price per call.
0.006 USDC je Aufruf · MCP video_trim
POST /v1/video-thumbnail
Takes a video (up to 24 MB) and returns the best poster frames: candidates are spread over the running time, and for each segment ffmpeg's thumbnail filter selects the frame closest to the segment average, which avoids transitions, flashes and motion blur. Candidates that are almost black or very flat are dropped. The best candidates come back as JPEG at the chosen width, each with timestamp and mean brightness, ranked by brightness balance and contrast. Runs locally with ffmpeg. Fixed price per call.
0.004 USDC je Aufruf · MCP video_thumbnail
POST /v1/video-gif
Takes a video (up to 24 MB) and returns the part from start_seconds, up to 15 seconds long, as an animated GIF built with a palette computed for exactly this clip (much cleaner gradients than the default palette), or as animated WebP, which is smaller and true-colour but not supported everywhere. Width, frame rate and looping are selectable. Output inline as base64, max 12 MB; if the GIF would be larger, lower width or frame rate is suggested. Runs locally with ffmpeg. Fixed price per call.
0.004 USDC je Aufruf · MCP video_gif
POST /v1/video-vertical
Takes a video of up to 3 minutes and returns it in vertical 9:16 format at 720x1280 or 1080x1920. Mode crop fills the frame by cutting the sides, with the horizontal focus position selectable from left (0) to right (1); mode blur keeps the whole picture and places it centred on a blurred, enlarged copy of itself, so nothing is lost. Sound is kept. Output MP4 (H.264/AAC) inline as base64, max 24 MB. Runs locally with ffmpeg. Billing per started video minute.
0.01 USDC je Aufruf · MCP video_vertical
POST /v1/video-contact-sheet
Takes a video (up to 24 MB) and returns one JPEG with columns × rows frames taken at evenly spaced times across the running time, each tile labelled with its timestamp, and the list of those times. Tile width, grid size and JPEG quality are selectable. Useful for a quick visual overview, for choosing a thumbnail, or as a single image to hand to a vision model instead of a whole video. Runs locally with ffmpeg; nothing leaves this machine. Fixed price per call.
0.004 USDC je Aufruf · MCP video_contact_sheet
POST /v1/video-audio-replace
Takes a video and an audio file (for example a dubbed track from /v1/dub, a voice-over or music) and returns the video with the new sound: mode replace drops the original audio, mode mix keeps it at original_volume underneath. The new audio is trimmed to the video length or padded with silence, optionally delayed by offset_seconds. The picture is copied, not re-encoded. Output MP4 with AAC inline as base64, max 24 MB. Runs locally with ffmpeg. Fixed price per call.
0.004 USDC je Aufruf · MCP video_audio_replace
POST /v1/video-watermark
Takes a video of up to 5 minutes and returns it with a text watermark rendered into the picture in DejaVu Sans, at top-left, top-right, bottom-left, bottom-right or centre, with selectable size relative to the picture height and opacity, optionally followed by a running timecode — useful for review copies and drafts. Sound is copied unchanged. Output MP4 (H.264/AAC) inline as base64, max 24 MB. Runs locally with ffmpeg. Billing per started video minute.
0.008 USDC je Aufruf · MCP video_watermark
POST /v1/video-black-detect
Takes a video of up to 30 minutes and finds, in one pass, segments where the picture is black (blackdetect), where it freezes (freezedetect) and where the sound drops out (silencedetect), each with start, end and duration, using minimum lengths and thresholds you can set. A summary says whether the file passes with no finding longer than the limits. Leading and trailing black is reported separately because it is often intended. Runs locally with ffmpeg; nothing leaves this machine. Billing per started video minute.
0.004 USDC je Aufruf · MCP video_black_detect
POST /v1/video-loudness
Takes a video of up to 15 minutes, measures the integrated loudness, true peak and loudness range of its soundtrack, and normalises it to the chosen standard with two-pass linear loudnorm, so the dynamics are kept and the target is met closely. The picture is copied without re-encoding. Loudness is measured again on the result and both measurements are returned. Output MP4 with AAC audio inline as base64, max 24 MB. Runs locally with ffmpeg. Billing per started video minute.
0.004 USDC je Aufruf · MCP video_loudness
POST /v1/media-chapters-embed
Takes a media file (up to 24 MB) and a list of chapters with start time and title — for example from the video digest, podcast show notes or topic segmentation — and returns the same file with real embedded chapters: MP4/M4A chapter atoms, Matroska chapters, or ID3 chapter frames for MP3. Audio and video are copied, not re-encoded. Chapters starting after the end are dropped and counted; the end of each chapter is the start of the next. Runs locally with ffmpeg. Fixed price per call.
0.003 USDC je Aufruf · MCP media_chapters_embed
POST /v1/video-subtitle-mux
Takes a video (up to 24 MB) and one to five SRT or WebVTT subtitle texts with language codes, and returns the video with each as a separate, switchable subtitle track tagged with its language, the first marked default. Picture and sound are copied, not re-encoded, so quality is unchanged and it is fast. MP4 uses mov_text (plays in QuickTime, browsers with players, most phones); MKV uses SRT tracks (VLC, mpv, Plex). Unlike /v1/burn-subtitles nothing is drawn into the picture. Runs locally with ffmpeg. Fixed price per call.
0.004 USDC je Aufruf · MCP video_subtitle_mux
POST /v1/podcast-spec-check
Takes an episode file (up to 24 MB) and checks it against widely used podcast delivery recommendations: MP3 or AAC container, bitrate of at least 64 kbit/s (mono) or 96 kbit/s (stereo), 44.1 or 48 kHz sample rate, integrated loudness of -16 LUFS ±1 for stereo (-19 for mono), true peak at most -1 dBTP, a title tag present, chapters present (recommendation only), and no more than 3 seconds of silence at the start and end. Every rule returns its measured value, the limit and pass, warn or fail, plus an overall verdict. Nothing is changed. Runs locally with ffmpeg. Fixed price per call.
0.004 USDC je Aufruf · MCP podcast_spec_check
POST /v1/id3-tags
Takes an audio file (MP3, M4A, Ogg, FLAC; up to 24 MB). Without set it returns all metadata tags, embedded chapters and whether a cover image is present. With set it writes the given fields — title, artist, album, album_artist, genre, date, track, comment, composer, publisher, copyright, language, description — as ID3v2.3 for MP3 or native tags for other containers, removes fields set to an empty string, copies the audio without re-encoding and returns the file together with the tags read back from it. Runs locally with ffmpeg. Fixed price per call.
0.002 USDC je Aufruf · MCP id3_tags
POST /v1/captions-check
Takes subtitle text in SRT or WebVTT and checks every cue against configurable rules: maximum characters per line (default 42), maximum lines per cue (2), reading speed in characters per second (default 17 for adults, 13 recommended for children), minimum duration (0.83 s) and maximum duration (7 s), overlapping cues, and gaps too short for the eye to register a change (under 2 frames). Defaults follow common streaming and broadcaster guidelines. Returned are counts per rule, a pass rate and every violation with cue number, time, measured value and text. Pure text processing; nothing is stored. Fixed price per call.
0.002 USDC je Aufruf · MCP captions_check
POST /v1/subtitle-translate
Takes subtitle text in SRT or WebVTT and a target language and returns the translated file: every cue is translated on its own so that number, order and timing of cues stay exactly as in the original, which is checked on each model answer. Line breaks inside a cue are joined for translation. Output in SRT or WebVTT. Translation by a language model at Groq, which does not train on inputs; disclosed in the answer. Machine translation, unreviewed. Billing per started 100 cues, fixed before payment from the file itself.
0.01 USDC je Aufruf · MCP subtitle_translate
POST /v1/subtitle-convert
Takes subtitle text in SRT or WebVTT (format detected automatically) and returns it in one or more target formats: SRT, WebVTT, ASS with a readable default style, TTML, JSON cue list or plain text. Cue settings and styling of the source are not carried over; timings and text are. Blocks that cannot be parsed are counted and reported instead of silently dropped. Pure text processing on this machine; nothing is stored. Fixed price per call.
0.001 USDC je Aufruf · MCP subtitle_convert
POST /v1/vocabulary
Takes a recording of up to 60 minutes in the language being learned and a learner level, and returns words and phrases worth learning — chosen for the level, skipping the most basic ones — each with the base form, translation into the learner's language, word type, an estimated CEFR level, and the exact example sentence from the recording with its timestamp so it can be listened to in context. Every finding carries a verbatim quote from the transcript; quotes are searched in the transcript and findings whose quote cannot be found are dropped and counted, so nothing invented passes through. Transcription by Deepgram with training opt-out, analysis by a language model at Groq, which does not train on inputs; both disclosed in every answer. Billing per started audio minute; a longer file than declared is refused and nothing is charged.
0.03 USDC je Aufruf · MCP vocabulary
POST /v1/listening-quiz
Takes a recording of up to 30 minutes and creates listening-comprehension exercises like those in language exams: multiple-choice questions with four options and true/false statements, at the chosen CEFR level, in the learner's or the recording's language. Every question comes with the correct answer and the exact passage (quote and timestamp) where the answer is heard, so learners can replay it. Every finding carries a verbatim quote from the transcript; quotes are searched in the transcript and findings whose quote cannot be found are dropped and counted, so nothing invented passes through. Transcription by Deepgram with training opt-out, analysis by a language model at Groq, which does not train on inputs; both disclosed in every answer. Billing per started audio minute; a longer file than declared is refused and nothing is charged.
0.03 USDC je Aufruf · MCP listening_quiz
POST /v1/media-probe-batch
Takes 1 to 25 media files by URL or inline (each up to 24 MB) and returns for each: duration in seconds and in started minutes (the value every per-minute service here expects as duration_minutes), container, audio and video codecs, channels, sample rate, resolution, frame rate, bitrate, size and SHA-256, plus detected file type. Files that cannot be read are reported with their error instead of failing the call. Runs locally with ffprobe; nothing leaves this machine. Billing per file.
0.001 USDC je Aufruf · MCP media_probe_batch
POST /v1/transcript-merge
Takes up to 20 transcript parts, each a list of segments with start, end and text, plus an optional speaker label and a time offset in seconds (where the part starts in the full recording). Offsets are applied, all segments are sorted by time, and the merged transcript is returned as a segment list, plain text with speaker labels, SRT and WebVTT. Overlapping segments from different speakers are kept and counted, which is normal for per-speaker tracks. Pure data processing; nothing is stored. Fixed price per call.
0.001 USDC je Aufruf · MCP transcript_merge
POST /v1/speaker-rename
Takes a transcript, SRT or WebVTT text and a mapping from labels to names, e.g. {"Speaker 1": "Anna Weber", "S2": "Interviewer"}, and replaces each label where it marks a speaker: at the start of a line before a colon, and inside WebVTT voice tags . Words inside sentences that merely look like a label are not touched. The answer counts replacements per label and lists speaker labels found in the text that have no name in the mapping. Pure text processing on this machine. Fixed price per call.
0.001 USDC je Aufruf · MCP speaker_rename
POST /v1/timestamps-shift
Takes SRT or WebVTT subtitles and corrects their timing in one of two ways: either with an offset in seconds and an optional speed factor (new = old × factor + offset, e.g. 25/23.976 for a frame-rate mismatch), or with two anchors — a cue number and the time where it really belongs, for two cues far apart — from which factor and offset are calculated and reported. Cues that would start before zero are clipped to zero and counted. Output in the input format or another one (SRT, WebVTT). Pure text processing on this machine. Fixed price per call.
0.001 USDC je Aufruf · MCP timestamps_shift
POST /v1/transcript-package
Uses the existing Deepgram and local media pipeline with one diarized transcription call. Subtitle cues split at speaker changes, pauses, six seconds or 84 characters. Unknown speakers remain null. Requires a lawful recording; submitted audio leaves this server for Deepgram, with the existing provider opt-out disclosure. Audio, transcript and subtitles are not retained. This synchronous request has no background job or callback.
0.03 USDC je Aufruf · MCP transcript_package
POST /v1/cost-estimate
Takes an audio or video file (up to 24 MB), measures its running time, derives the started minutes to declare as duration_minutes, and returns for every service of this hub that bills by duration the exact price it would quote — computed with the same quote function that produces its 402 challenge — or the reason it cannot take the file (too long). Services with other price units (per call, per file, per characters) are listed with their unit price. Sorted by price. Use it to plan a pipeline before paying. Fixed price per call.
0.001 USDC je Aufruf · MCP cost_estimate
POST /v1/topic-segments
Takes a recording of up to 120 minutes and returns its topic structure: segments that start where the subject really changes, each with a topic label of up to eight words, keywords, a one-sentence summary, start and end time and the spoken text of the segment. Boundaries are chosen by a language model as sentence numbers only, so they always fall on sentence starts with recogniser timestamps. Maximum number of segments and output language are selectable. Transcription by Deepgram with training opt-out, segmentation by Groq. Billing per started audio minute.
0.025 USDC je Aufruf · MCP topic_segments
POST /v1/oss-opencv-planar-camera-calibrate
Takes matched object and image points from multiple views of a planar calibration target and returns the camera matrix, five distortion coefficients and the RMS reprojection error that the fit actually achieved. The error figure is the point: it tells a caller whether the calibration is usable before anything is built on top of it, instead of handing back numbers that look plausible.
0.003 USDC je Aufruf · MCP oss_opencv_planar_camera_calibrate
POST /v1/oss-opencv-stereo-rig-calibrate
Given paired calibration observations and the intrinsics of both cameras, this computes the rotation and translation between them and derives everything a stereo pipeline needs downstream: rectification transforms for both views, both projection matrices, and the disparity-to-depth mapping. The RMS error in pixels says how well the rig geometry actually fits the data.
0.003 USDC je Aufruf · MCP oss_opencv_stereo_rig_calibrate
POST /v1/oss-opencv-landmark-camera-pose
Solves for the rigid transform between an object's coordinate frame and the camera, given 3D landmark coordinates, where those landmarks appear in the image, and the camera matrix and distortion. Returns the rotation and translation together with the reprojection RMSE, so a caller can tell a well-constrained pose from one that merely converged. This is the standard step for placing a known object in a scene or locating a camera against a known marker.
0.002 USDC je Aufruf · MCP oss_opencv_landmark_camera_pose
POST /v1/oss-opencv-robust-planar-homography
Fits a 2D projective transform between two point sets with RANSAC at a caller-chosen reprojection threshold, and returns both the homography and the inlier mask. The mask is what makes this useful beyond a plain fit: bad correspondences are named rather than quietly averaged in, so a caller can re-run detection, drop a frame or raise an alarm. Suitable for document rectification, planar tracking and image stitching where the scene really is flat.
0.002 USDC je Aufruf · MCP oss_opencv_robust_planar_homography
POST /v1/oss-opencv-paired-point-triangulate
Triangulates 3D positions from corresponding points in two calibrated views using the supplied projection matrices. Degenerate cases are reported honestly: a correspondence whose rays are near-parallel has no finite intersection, and it comes back as null with its position in the finite mask, instead of as an enormous coordinate that silently poisons whatever consumes it. That makes the result safe to feed into a fitting step without a sanity filter of your own.
0.002 USDC je Aufruf · MCP oss_opencv_paired_point_triangulate
POST /v1/oss-opencv-rectified-stereo-disparity
Runs semi-global block matching over a rectified grayscale stereo pair and returns per-pixel disparity together with the count of pixels that could actually be matched. Pixels with no reliable match stay unmatched rather than being interpolated, so occlusions and textureless regions are visible in the output instead of hidden by plausible-looking values. Disparities are positive and bounded at 16 pixels, which suits small-baseline rigs and close range.
0.004 USDC je Aufruf · MCP oss_opencv_rectified_stereo_disparity
POST /v1/oss-opencv-dense-frame-optical-flow
Computes dense Farneback optical flow between two consecutive grayscale frames and returns the horizontal and vertical displacement of every pixel. Unlike sparse tracking this covers the whole image, which is what you want for measuring motion in regions with no distinct features to track — smoke, water, crowds, a panning background. Both frames must be the same size and should come from the same camera at a short interval.
0.004 USDC je Aufruf · MCP oss_opencv_dense_frame_optical_flow
POST /v1/oss-opencv-external-contour-metrics
Finds the external contours in a caller-supplied binary mask and reports, for each, its area, perimeter, centroid and bounding rectangle, plus the total foreground pixel count. The division of labour is deliberate: segmentation is a domain decision, so the mask comes from you and the measurement comes from here, which keeps the numbers reproducible and independent of any threshold this service might have chosen.
0.002 USDC je Aufruf · MCP oss_opencv_external_contour_metrics
POST /v1/oss-opencv-robot-hand-eye-calibrate
Solves the hand-eye problem: given a series of gripper-to-base poses read from the robot and the matching target-to-camera poses seen by the camera, it recovers the rigid transform between camera and gripper that stays constant as the arm moves. This is what lets a robot act on what its camera sees. The poses must be genuinely synchronized — a pairing that is off by one sample produces a confident and entirely wrong transform, and nothing in the data reveals it.
0.003 USDC je Aufruf · MCP oss_opencv_robot_hand_eye_calibrate
POST /v1/oss-opencv-calibrated-lens-undistort
Resamples a grayscale image to remove radial and tangential lens distortion, using the camera matrix and five distortion coefficients you supply — typically from a planar calibration. Dimensions and camera matrix are preserved, so the corrected image drops into an existing pipeline without any change to geometry downstream. Because the output frame is unchanged, strongly distorted corners are pushed outside the image and are simply lost rather than being retained in a larger canvas.
0.002 USDC je Aufruf · MCP oss_opencv_calibrated_lens_undistort
POST /v1/baumarkt/media/word-density
Calculate recognized words per recorded minute without acoustic or fluency inference. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_word_density
POST /v1/baumarkt/media/word-coverage
Measure union coverage of recognized word timestamps within the recording. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_word_coverage
POST /v1/baumarkt/media/speaker-time
Allocate recognized word durations by anonymous speaker label, including unknown labels. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_speaker_time
POST /v1/baumarkt/media/speaker-density
Calculate word pace per recognized speaking interval for each anonymous label. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_speaker_density
POST /v1/baumarkt/media/unknown-speaker-review
Produce a timestamped manual-review list for unknown speaker labels. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_unknown_speaker_review
POST /v1/baumarkt/media/word-gap-index
Index gaps between recognized words without claiming acoustic silence. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_word_gap_index
POST /v1/baumarkt/media/cue-gap-index
Index subtitle display gaps for caption coverage review. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_cue_gap_index
POST /v1/baumarkt/media/gap-cut-proposals
Propose cuts inside two-second word gaps with safety padding; never execute. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_gap_cut_proposals
POST /v1/baumarkt/media/edge-trim-proposal
Propose outer trim boundaries from recognized words with quarter-second padding. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_edge_trim_proposal
POST /v1/baumarkt/media/confidence-histogram
Separate provider confidence bands from unknown confidence values. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_confidence_histogram
POST /v1/baumarkt/media/cue-reading-speed
Measure subtitle Unicode-codepoint reading speed and its distribution. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_cue_reading_speed
POST /v1/baumarkt/media/subtitle-review-flags
Flag fast, short and text-heavy cues for explicit editorial review. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_subtitle_review_flags
POST /v1/baumarkt/media/cue-duration-distribution
Summarize cue display durations and locate the shortest source cue. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_cue_duration_distribution
POST /v1/baumarkt/media/cue-word-load
Measure word load and word rate per subtitle cue. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_cue_word_load
POST /v1/baumarkt/media/subtitle-line-balance
Create a two-line caption layout without dropping source text and mark overflow. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_subtitle_line_balance
POST /v1/baumarkt/media/frame-quantized-cues
Convert source cue ranges to outward-rounded25fps frame intervals. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_frame_quantized_cues
POST /v1/baumarkt/media/edit-decision-list
Build a labeled speaker-turn edit range list without executing edits. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_edit_decision_list
POST /v1/baumarkt/media/ffmpeg-trim-plan
Produce path-free FFmpeg filter expressions for source-backed speaker turns. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_ffmpeg_trim_plan
POST /v1/baumarkt/media/marker-xml-export
Create escaped XML editor markers with actual speaker-turn source ranges. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_marker_xml_export
POST /v1/baumarkt/media/word-csv-export
Export a spreadsheet-safe timestamped-word table with speaker/confidence columns. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_word_csv_export
POST /v1/baumarkt/media/search-token-index
Build a Unicode lowercase token-to-word-time search index without stemming. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_search_token_index
POST /v1/baumarkt/media/repeated-token-review
Identify consecutive repeated recognized tokens without deleting speech. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_repeated_token_review
POST /v1/baumarkt/media/speaker-cue-crosswalk
Cross-reference subtitle cues with contained source words and flag label mismatch. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_speaker_cue_crosswalk
POST /v1/baumarkt/media/cue-word-coverage
Identify words not fully contained in any subtitle cue. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_cue_word_coverage
POST /v1/baumarkt/media/cue-sha256-register
Compute stable source cue SHA256 digests for caller-managed caption change detection. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_cue_sha256_register
POST /v1/baumarkt/media/literal-redaction-plan
Locate caller-specified literal redaction strings; no semantic PII detection. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_literal_redaction_plan
POST /v1/baumarkt/media/keyword-clip-ranges
Propose padded cue clips around caller-specified literal keywords. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_keyword_clip_ranges
POST /v1/baumarkt/media/chapter-keyword-markers
Create source-time chapter markers for caller-specified literal terms. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_chapter_keyword_markers
POST /v1/baumarkt/media/long-gap-review-worklist
Create editorial audio-review tasks for long recognized-word gaps. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_long_gap_review_worklist
POST /v1/baumarkt/media/confidence-cue-worklist
Group low-confidence recognized words into source subtitle review tasks. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_confidence_cue_worklist
POST /v1/baumarkt/media/spoken-numeric-token-index
Index recognized tokens containing digits without interpreting spelled numbers. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_spoken_numeric_token_index
POST /v1/baumarkt/media/punctuation-edit-index
Locate provider-punctuated sentence-ending tokens as candidate edit boundaries. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_punctuation_edit_index
POST /v1/baumarkt/media/podcast-sponsors-literal-index
Timestamped source search for sponsor handoff mentions; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_podcast_sponsors_literal_index
POST /v1/baumarkt/media/podcast-subscription-literal-index
Timestamped source search for subscription call-to-action mentions; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_podcast_subscription_literal_index
POST /v1/baumarkt/media/podcast-production-literal-index
Timestamped source search for production equipment mentions; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_podcast_production_literal_index
POST /v1/baumarkt/media/interview-career-literal-index
Timestamped source search for career interview passages; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_interview_career_literal_index
POST /v1/baumarkt/media/interview-education-literal-index
Timestamped source search for education interview passages; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_interview_education_literal_index
POST /v1/baumarkt/media/interview-projects-literal-index
Timestamped source search for project interview passages; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_interview_projects_literal_index
POST /v1/baumarkt/media/interview-feedback-literal-index
Timestamped source search for feedback interview passages; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_interview_feedback_literal_index
POST /v1/baumarkt/media/sales-budget-literal-index
Timestamped source search for sales budget passages; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_sales_budget_literal_index
POST /v1/baumarkt/media/sales-procurement-literal-index
Timestamped source search for procurement passages; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_sales_procurement_literal_index
POST /v1/baumarkt/media/sales-pricing-literal-index
Timestamped source search for pricing discussion passages; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_sales_pricing_literal_index
POST /v1/baumarkt/media/sales-objection-literal-index
Timestamped source search for customer objection wording; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_sales_objection_literal_index
POST /v1/baumarkt/media/sales-competitor-literal-index
Timestamped source search for competition wording; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_sales_competitor_literal_index
POST /v1/baumarkt/media/sales-onboarding-literal-index
Timestamped source search for onboarding discussion passages; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_sales_onboarding_literal_index
POST /v1/baumarkt/media/support-incident-literal-index
Timestamped source search for incident vocabulary passages; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_support_incident_literal_index
POST /v1/baumarkt/media/support-escalation-literal-index
Timestamped source search for escalation wording; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_support_escalation_literal_index
POST /v1/baumarkt/media/support-refund-literal-index
Timestamped source search for refund request wording; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_support_refund_literal_index
POST /v1/baumarkt/media/support-delivery-literal-index
Timestamped source search for shipment support wording; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_support_delivery_literal_index
POST /v1/baumarkt/media/support-authentication-literal-index
Timestamped source search for authentication support wording; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_support_authentication_literal_index
POST /v1/baumarkt/media/support-billing-literal-index
Timestamped source search for billing support wording; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_support_billing_literal_index
POST /v1/baumarkt/media/engineering-deployment-literal-index
Timestamped source search for deployment discussion passages; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_engineering_deployment_literal_index
POST /v1/baumarkt/media/engineering-bug-literal-index
Timestamped source search for defect-report wording; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_engineering_bug_literal_index
POST /v1/baumarkt/media/engineering-api-literal-index
Timestamped source search for API design discussion passages; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_engineering_api_literal_index
POST /v1/baumarkt/media/engineering-database-literal-index
Timestamped source search for database discussion passages; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_engineering_database_literal_index
POST /v1/baumarkt/media/engineering-tests-literal-index
Timestamped source search for test planning passages; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_engineering_tests_literal_index
POST /v1/baumarkt/media/engineering-security-literal-index
Timestamped source search for security discussion wording; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_engineering_security_literal_index
POST /v1/baumarkt/media/engineering-performance-literal-index
Timestamped source search for performance vocabulary passages; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_engineering_performance_literal_index
POST /v1/baumarkt/media/engineering-accessibility-literal-index
Timestamped source search for accessibility discussion wording; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_engineering_accessibility_literal_index
POST /v1/baumarkt/media/engineering-roadmap-literal-index
Timestamped source search for roadmap discussion wording; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_engineering_roadmap_literal_index
POST /v1/baumarkt/media/logistics-inventory-literal-index
Timestamped source search for inventory planning passages; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_logistics_inventory_literal_index
POST /v1/baumarkt/media/logistics-loading-literal-index
Timestamped source search for loading discussion wording; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_logistics_loading_literal_index
POST /v1/baumarkt/media/logistics-routing-literal-index
Timestamped source search for dispatch planning passages; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_logistics_routing_literal_index
POST /v1/baumarkt/media/logistics-shortage-literal-index
Timestamped source search for shortage discussion wording; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_logistics_shortage_literal_index
POST /v1/baumarkt/media/logistics-damage-literal-index
Timestamped source search for damage report passages; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_logistics_damage_literal_index
POST /v1/baumarkt/media/logistics-return-literal-index
Timestamped source search for return planning wording; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_logistics_return_literal_index
POST /v1/baumarkt/media/finance-ledger-literal-index
Timestamped source search for bookkeeping vocabulary passages; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_finance_ledger_literal_index
POST /v1/baumarkt/media/finance-cashflow-literal-index
Timestamped source search for cashflow discussion wording; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_finance_cashflow_literal_index
POST /v1/baumarkt/media/finance-tax-literal-index
Timestamped source search for tax discussion vocabulary, without advice; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_finance_tax_literal_index
POST /v1/baumarkt/media/finance-forecast-literal-index
Timestamped source search for forecast discussion wording; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_finance_forecast_literal_index
POST /v1/baumarkt/media/finance-collections-literal-index
Timestamped source search for collections discussion passages; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_finance_collections_literal_index
POST /v1/baumarkt/media/finance-audit-literal-index
Timestamped source search for audit discussion wording; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_finance_audit_literal_index
POST /v1/baumarkt/media/hr-recruiting-literal-index
Timestamped source search for recruiting discussion wording; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_hr_recruiting_literal_index
POST /v1/baumarkt/media/hr-training-literal-index
Timestamped source search for training discussion passages; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_hr_training_literal_index
POST /v1/baumarkt/media/hr-workload-literal-index
Timestamped source search for workload discussion wording; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_hr_workload_literal_index
POST /v1/baumarkt/media/hr-leave-literal-index
Timestamped source search for leave planning wording; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_hr_leave_literal_index
POST /v1/baumarkt/media/hr-payroll-literal-index
Timestamped source search for payroll discussion vocabulary; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_hr_payroll_literal_index
POST /v1/baumarkt/media/hr-conflict-literal-index
Timestamped source search for conflict discussion wording; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_hr_conflict_literal_index
POST /v1/baumarkt/media/construction-materials-literal-index
Timestamped source search for material planning passages; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_construction_materials_literal_index
POST /v1/baumarkt/media/construction-permit-literal-index
Timestamped source search for permit discussion wording; no legal assessment; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_construction_permit_literal_index
POST /v1/baumarkt/media/construction-defect-literal-index
Timestamped source search for construction-defect report passages; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_construction_defect_literal_index
POST /v1/baumarkt/media/construction-safety-literal-index
Timestamped source search for safety briefing wording; no safety certification; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_construction_safety_literal_index
POST /v1/baumarkt/media/manufacturing-quality-literal-index
Timestamped source search for quality discussion wording; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_manufacturing_quality_literal_index
POST /v1/baumarkt/media/manufacturing-maintenance-literal-index
Timestamped source search for maintenance planning passages; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_manufacturing_maintenance_literal_index
POST /v1/baumarkt/media/manufacturing-capacity-literal-index
Timestamped source search for capacity discussion passages; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_manufacturing_capacity_literal_index
POST /v1/baumarkt/media/manufacturing-supplier-literal-index
Timestamped source search for supplier discussion passages; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_manufacturing_supplier_literal_index
POST /v1/baumarkt/media/research-hypothesis-literal-index
Timestamped source search for research hypothesis wording; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_research_hypothesis_literal_index
POST /v1/baumarkt/media/research-experiment-literal-index
Timestamped source search for experimental discussion wording; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_research_experiment_literal_index
POST /v1/baumarkt/media/research-dataset-literal-index
Timestamped source search for dataset discussion wording; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_research_dataset_literal_index
POST /v1/baumarkt/media/research-publication-literal-index
Timestamped source search for publication planning passages; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_research_publication_literal_index
POST /v1/baumarkt/media/legal-contract-literals-literal-index
Timestamped source search for contract vocabulary only, no legal interpretation; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_legal_contract_literals_literal_index
POST /v1/baumarkt/media/legal-evidence-literals-literal-index
Timestamped source search for evidence vocabulary only, no legal assessment; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_legal_evidence_literals_literal_index
POST /v1/baumarkt/media/clinical-appointment-literals-literal-index
Timestamped source search for appointment vocabulary only, no medical assessment; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_clinical_appointment_literals_literal_index
POST /v1/baumarkt/media/clinical-medication-literals-literal-index
Timestamped source search for medication vocabulary only, no dose or clinical inference; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims.
0.031 USDC je Aufruf · MCP media_clinical_medication_literals_literal_index
POST /v1/baumarkt/media/clinical-symptom-literals-literal-index
Timestamped source search for symptom vocabulary only, no diagnostic claim; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_clinical_symptom_literals_literal_index
POST /v1/baumarkt/media/education-assessment-literal-index
Timestamped source search for assessment planning wording; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_education_assessment_literal_index
POST /v1/baumarkt/media/education-curriculum-literal-index
Timestamped source search for curriculum discussion wording; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_education_curriculum_literal_index
POST /v1/baumarkt/media/events-venue-literal-index
Timestamped source search for venue planning wording; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_events_venue_literal_index
POST /v1/baumarkt/media/events-catering-literal-index
Timestamped source search for catering planning wording; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_events_catering_literal_index
POST /v1/baumarkt/media/marketing-campaign-literal-index
Timestamped source search for campaign discussion wording; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_marketing_campaign_literal_index
POST /v1/baumarkt/media/marketing-consent-literal-index
Timestamped source search for consent vocabulary, no legal conclusion; literal vocabulary only. Reuses exactly one existing qualified transcript-package request. Source audio leaves the server for the existing Deepgram processor; existing provider disclosure and cost/margin retained. Deterministic timestamps/text processing only; no acoustic VAD, speaker identity or specialist accuracy claims. Base motor quote plus0.001USDC; article fails before settlement if the motor fails.
0.031 USDC je Aufruf · MCP media_marketing_consent_literal_index
POST /v1/baumarkt/media/word-density/snapshot-compare
Compare Calculate recognized words per recorded minute without acoustic or fluency inference. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_word_density_snapshot_compare
POST /v1/baumarkt/media/word-coverage/snapshot-compare
Compare Measure union coverage of recognized word timestamps within the recording. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_word_coverage_snapshot_compare
POST /v1/baumarkt/media/speaker-time/snapshot-compare
Compare Allocate recognized word durations by anonymous speaker label, including unknown labels. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_speaker_time_snapshot_compare
POST /v1/baumarkt/media/speaker-density/snapshot-compare
Compare Calculate word pace per recognized speaking interval for each anonymous label. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_speaker_density_snapshot_compare
POST /v1/baumarkt/media/unknown-speaker-review/snapshot-compare
Compare Produce a timestamped manual-review list for unknown speaker labels. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_unknown_speaker_review_snapshot_compare
POST /v1/baumarkt/media/word-gap-index/snapshot-compare
Compare Index gaps between recognized words without claiming acoustic silence. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_word_gap_index_snapshot_compare
POST /v1/baumarkt/media/cue-gap-index/snapshot-compare
Compare Index subtitle display gaps for caption coverage review. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_cue_gap_index_snapshot_compare
POST /v1/baumarkt/media/gap-cut-proposals/snapshot-compare
Compare Propose cuts inside two-second word gaps with safety padding; never execute. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_gap_cut_proposals_snapshot_compare
POST /v1/baumarkt/media/edge-trim-proposal/snapshot-compare
Compare Propose outer trim boundaries from recognized words with quarter-second padding. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_edge_trim_proposal_snapshot_compare
POST /v1/baumarkt/media/confidence-histogram/snapshot-compare
Compare Separate provider confidence bands from unknown confidence values. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_confidence_histogram_snapshot_compare
POST /v1/baumarkt/media/cue-reading-speed/snapshot-compare
Compare Measure subtitle Unicode-codepoint reading speed and its distribution. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_cue_reading_speed_snapshot_compare
POST /v1/baumarkt/media/subtitle-review-flags/snapshot-compare
Compare Flag fast, short and text-heavy cues for explicit editorial review. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_subtitle_review_flags_snapshot_compare
POST /v1/baumarkt/media/cue-duration-distribution/snapshot-compare
Compare Summarize cue display durations and locate the shortest source cue. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_cue_duration_distribution_snapshot_compare
POST /v1/baumarkt/media/cue-word-load/snapshot-compare
Compare Measure word load and word rate per subtitle cue. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_cue_word_load_snapshot_compare
POST /v1/baumarkt/media/subtitle-line-balance/snapshot-compare
Compare Create a two-line caption layout without dropping source text and mark overflow. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_subtitle_line_balance_snapshot_compare
POST /v1/baumarkt/media/frame-quantized-cues/snapshot-compare
Compare Convert source cue ranges to outward-rounded25fps frame intervals. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_frame_quantized_cues_snapshot_compare
POST /v1/baumarkt/media/edit-decision-list/snapshot-compare
Compare Build a labeled speaker-turn edit range list without executing edits. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_edit_decision_list_snapshot_compare
POST /v1/baumarkt/media/ffmpeg-trim-plan/snapshot-compare
Compare Produce path-free FFmpeg filter expressions for source-backed speaker turns. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_ffmpeg_trim_plan_snapshot_compare
POST /v1/baumarkt/media/marker-xml-export/snapshot-compare
Compare Create escaped XML editor markers with actual speaker-turn source ranges. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_marker_xml_export_snapshot_compare
POST /v1/baumarkt/media/word-csv-export/snapshot-compare
Compare Export a spreadsheet-safe timestamped-word table with speaker/confidence columns. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_word_csv_export_snapshot_compare
POST /v1/baumarkt/media/search-token-index/snapshot-compare
Compare Build a Unicode lowercase token-to-word-time search index without stemming. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_search_token_index_snapshot_compare
POST /v1/baumarkt/media/repeated-token-review/snapshot-compare
Compare Identify consecutive repeated recognized tokens without deleting speech. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_repeated_token_review_snapshot_compare
POST /v1/baumarkt/media/speaker-cue-crosswalk/snapshot-compare
Compare Cross-reference subtitle cues with contained source words and flag label mismatch. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_speaker_cue_crosswalk_snapshot_compare
POST /v1/baumarkt/media/cue-word-coverage/snapshot-compare
Compare Identify words not fully contained in any subtitle cue. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_cue_word_coverage_snapshot_compare
POST /v1/baumarkt/media/cue-sha256-register/snapshot-compare
Compare Compute stable source cue SHA256 digests for caller-managed caption change detection. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_cue_sha256_register_snapshot_compare
POST /v1/baumarkt/media/literal-redaction-plan/snapshot-compare
Compare Locate caller-specified literal redaction strings; no semantic PII detection. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_literal_redaction_plan_snapshot_compare
POST /v1/baumarkt/media/keyword-clip-ranges/snapshot-compare
Compare Propose padded cue clips around caller-specified literal keywords. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_keyword_clip_ranges_snapshot_compare
POST /v1/baumarkt/media/chapter-keyword-markers/snapshot-compare
Compare Create source-time chapter markers for caller-specified literal terms. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_chapter_keyword_markers_snapshot_compare
POST /v1/baumarkt/media/long-gap-review-worklist/snapshot-compare
Compare Create editorial audio-review tasks for long recognized-word gaps. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_long_gap_review_worklist_snapshot_compare
POST /v1/baumarkt/media/confidence-cue-worklist/snapshot-compare
Compare Group low-confidence recognized words into source subtitle review tasks. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_confidence_cue_worklist_snapshot_compare
POST /v1/baumarkt/media/spoken-numeric-token-index/snapshot-compare
Compare Index recognized tokens containing digits without interpreting spelled numbers. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_spoken_numeric_token_index_snapshot_compare
POST /v1/baumarkt/media/punctuation-edit-index/snapshot-compare
Compare Locate provider-punctuated sentence-ending tokens as candidate edit boundaries. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_punctuation_edit_index_snapshot_compare
POST /v1/baumarkt/media/podcast-sponsors-literal-index/snapshot-compare
Compare Timestamped source search for sponsor handoff mentions; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_podcast_sponsors_literal_index_snapshot_compare
POST /v1/baumarkt/media/podcast-subscription-literal-index/snapshot-compare
Compare Timestamped source search for subscription call-to-action mentions; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_podcast_subscription_literal_index_snapshot_compare
POST /v1/baumarkt/media/podcast-production-literal-index/snapshot-compare
Compare Timestamped source search for production equipment mentions; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_podcast_production_literal_index_snapshot_compare
POST /v1/baumarkt/media/interview-career-literal-index/snapshot-compare
Compare Timestamped source search for career interview passages; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_interview_career_literal_index_snapshot_compare
POST /v1/baumarkt/media/interview-education-literal-index/snapshot-compare
Compare Timestamped source search for education interview passages; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_interview_education_literal_index_snapshot_compare
POST /v1/baumarkt/media/interview-projects-literal-index/snapshot-compare
Compare Timestamped source search for project interview passages; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_interview_projects_literal_index_snapshot_compare
POST /v1/baumarkt/media/interview-feedback-literal-index/snapshot-compare
Compare Timestamped source search for feedback interview passages; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_interview_feedback_literal_index_snapshot_compare
POST /v1/baumarkt/media/sales-budget-literal-index/snapshot-compare
Compare Timestamped source search for sales budget passages; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_sales_budget_literal_index_snapshot_compare
POST /v1/baumarkt/media/sales-procurement-literal-index/snapshot-compare
Compare Timestamped source search for procurement passages; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_sales_procurement_literal_index_snapshot_compare
POST /v1/baumarkt/media/sales-pricing-literal-index/snapshot-compare
Compare Timestamped source search for pricing discussion passages; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_sales_pricing_literal_index_snapshot_compare
POST /v1/baumarkt/media/sales-objection-literal-index/snapshot-compare
Compare Timestamped source search for customer objection wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_sales_objection_literal_index_snapshot_compare
POST /v1/baumarkt/media/sales-competitor-literal-index/snapshot-compare
Compare Timestamped source search for competition wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_sales_competitor_literal_index_snapshot_compare
POST /v1/baumarkt/media/sales-onboarding-literal-index/snapshot-compare
Compare Timestamped source search for onboarding discussion passages; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_sales_onboarding_literal_index_snapshot_compare
POST /v1/baumarkt/media/support-incident-literal-index/snapshot-compare
Compare Timestamped source search for incident vocabulary passages; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_support_incident_literal_index_snapshot_compare
POST /v1/baumarkt/media/support-escalation-literal-index/snapshot-compare
Compare Timestamped source search for escalation wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_support_escalation_literal_index_snapshot_compare
POST /v1/baumarkt/media/support-refund-literal-index/snapshot-compare
Compare Timestamped source search for refund request wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_support_refund_literal_index_snapshot_compare
POST /v1/baumarkt/media/support-delivery-literal-index/snapshot-compare
Compare Timestamped source search for shipment support wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_support_delivery_literal_index_snapshot_compare
POST /v1/baumarkt/media/support-authentication-literal-index/snapshot-compare
Compare Timestamped source search for authentication support wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_support_authentication_literal_index_snapshot_compare
POST /v1/baumarkt/media/support-billing-literal-index/snapshot-compare
Compare Timestamped source search for billing support wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_support_billing_literal_index_snapshot_compare
POST /v1/baumarkt/media/engineering-deployment-literal-index/snapshot-compare
Compare Timestamped source search for deployment discussion passages; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_engineering_deployment_literal_index_snapshot_compare
POST /v1/baumarkt/media/engineering-bug-literal-index/snapshot-compare
Compare Timestamped source search for defect-report wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_engineering_bug_literal_index_snapshot_compare
POST /v1/baumarkt/media/engineering-api-literal-index/snapshot-compare
Compare Timestamped source search for API design discussion passages; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_engineering_api_literal_index_snapshot_compare
POST /v1/baumarkt/media/engineering-database-literal-index/snapshot-compare
Compare Timestamped source search for database discussion passages; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_engineering_database_literal_index_snapshot_compare
POST /v1/baumarkt/media/engineering-tests-literal-index/snapshot-compare
Compare Timestamped source search for test planning passages; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_engineering_tests_literal_index_snapshot_compare
POST /v1/baumarkt/media/engineering-security-literal-index/snapshot-compare
Compare Timestamped source search for security discussion wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_engineering_security_literal_index_snapshot_compare
POST /v1/baumarkt/media/engineering-performance-literal-index/snapshot-compare
Compare Timestamped source search for performance vocabulary passages; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_engineering_performance_literal_index_snapshot_compare
POST /v1/baumarkt/media/engineering-accessibility-literal-index/snapshot-compare
Compare Timestamped source search for accessibility discussion wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_engineering_accessibility_literal_index_snapshot_compare
POST /v1/baumarkt/media/engineering-roadmap-literal-index/snapshot-compare
Compare Timestamped source search for roadmap discussion wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_engineering_roadmap_literal_index_snapshot_compare
POST /v1/baumarkt/media/logistics-inventory-literal-index/snapshot-compare
Compare Timestamped source search for inventory planning passages; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_logistics_inventory_literal_index_snapshot_compare
POST /v1/baumarkt/media/logistics-loading-literal-index/snapshot-compare
Compare Timestamped source search for loading discussion wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_logistics_loading_literal_index_snapshot_compare
POST /v1/baumarkt/media/logistics-routing-literal-index/snapshot-compare
Compare Timestamped source search for dispatch planning passages; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_logistics_routing_literal_index_snapshot_compare
POST /v1/baumarkt/media/logistics-shortage-literal-index/snapshot-compare
Compare Timestamped source search for shortage discussion wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_logistics_shortage_literal_index_snapshot_compare
POST /v1/baumarkt/media/logistics-damage-literal-index/snapshot-compare
Compare Timestamped source search for damage report passages; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_logistics_damage_literal_index_snapshot_compare
POST /v1/baumarkt/media/logistics-return-literal-index/snapshot-compare
Compare Timestamped source search for return planning wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_logistics_return_literal_index_snapshot_compare
POST /v1/baumarkt/media/finance-ledger-literal-index/snapshot-compare
Compare Timestamped source search for bookkeeping vocabulary passages; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_finance_ledger_literal_index_snapshot_compare
POST /v1/baumarkt/media/finance-cashflow-literal-index/snapshot-compare
Compare Timestamped source search for cashflow discussion wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_finance_cashflow_literal_index_snapshot_compare
POST /v1/baumarkt/media/finance-tax-literal-index/snapshot-compare
Compare Timestamped source search for tax discussion vocabulary, without advice; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_finance_tax_literal_index_snapshot_compare
POST /v1/baumarkt/media/finance-forecast-literal-index/snapshot-compare
Compare Timestamped source search for forecast discussion wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_finance_forecast_literal_index_snapshot_compare
POST /v1/baumarkt/media/finance-collections-literal-index/snapshot-compare
Compare Timestamped source search for collections discussion passages; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_finance_collections_literal_index_snapshot_compare
POST /v1/baumarkt/media/finance-audit-literal-index/snapshot-compare
Compare Timestamped source search for audit discussion wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_finance_audit_literal_index_snapshot_compare
POST /v1/baumarkt/media/hr-recruiting-literal-index/snapshot-compare
Compare Timestamped source search for recruiting discussion wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_hr_recruiting_literal_index_snapshot_compare
POST /v1/baumarkt/media/hr-training-literal-index/snapshot-compare
Compare Timestamped source search for training discussion passages; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_hr_training_literal_index_snapshot_compare
POST /v1/baumarkt/media/hr-workload-literal-index/snapshot-compare
Compare Timestamped source search for workload discussion wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_hr_workload_literal_index_snapshot_compare
POST /v1/baumarkt/media/hr-leave-literal-index/snapshot-compare
Compare Timestamped source search for leave planning wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_hr_leave_literal_index_snapshot_compare
POST /v1/baumarkt/media/hr-payroll-literal-index/snapshot-compare
Compare Timestamped source search for payroll discussion vocabulary; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_hr_payroll_literal_index_snapshot_compare
POST /v1/baumarkt/media/hr-conflict-literal-index/snapshot-compare
Compare Timestamped source search for conflict discussion wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_hr_conflict_literal_index_snapshot_compare
POST /v1/baumarkt/media/construction-materials-literal-index/snapshot-compare
Compare Timestamped source search for material planning passages; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_construction_materials_literal_index_snapshot_compare
POST /v1/baumarkt/media/construction-permit-literal-index/snapshot-compare
Compare Timestamped source search for permit discussion wording; no legal assessment; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_construction_permit_literal_index_snapshot_compare
POST /v1/baumarkt/media/construction-defect-literal-index/snapshot-compare
Compare Timestamped source search for construction-defect report passages; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_construction_defect_literal_index_snapshot_compare
POST /v1/baumarkt/media/construction-safety-literal-index/snapshot-compare
Compare Timestamped source search for safety briefing wording; no safety certification; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_construction_safety_literal_index_snapshot_compare
POST /v1/baumarkt/media/manufacturing-quality-literal-index/snapshot-compare
Compare Timestamped source search for quality discussion wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_manufacturing_quality_literal_index_snapshot_compare
POST /v1/baumarkt/media/manufacturing-maintenance-literal-index/snapshot-compare
Compare Timestamped source search for maintenance planning passages; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_manufacturing_maintenance_literal_index_snapshot_compare
POST /v1/baumarkt/media/manufacturing-capacity-literal-index/snapshot-compare
Compare Timestamped source search for capacity discussion passages; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_manufacturing_capacity_literal_index_snapshot_compare
POST /v1/baumarkt/media/manufacturing-supplier-literal-index/snapshot-compare
Compare Timestamped source search for supplier discussion passages; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_manufacturing_supplier_literal_index_snapshot_compare
POST /v1/baumarkt/media/research-hypothesis-literal-index/snapshot-compare
Compare Timestamped source search for research hypothesis wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_research_hypothesis_literal_index_snapshot_compare
POST /v1/baumarkt/media/research-experiment-literal-index/snapshot-compare
Compare Timestamped source search for experimental discussion wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_research_experiment_literal_index_snapshot_compare
POST /v1/baumarkt/media/research-dataset-literal-index/snapshot-compare
Compare Timestamped source search for dataset discussion wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_research_dataset_literal_index_snapshot_compare
POST /v1/baumarkt/media/research-publication-literal-index/snapshot-compare
Compare Timestamped source search for publication planning passages; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_research_publication_literal_index_snapshot_compare
POST /v1/baumarkt/media/legal-contract-literals-literal-index/snapshot-compare
Compare Timestamped source search for contract vocabulary only, no legal interpretation; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_legal_contract_literals_literal_index_snapshot_compare
POST /v1/baumarkt/media/legal-evidence-literals-literal-index/snapshot-compare
Compare Timestamped source search for evidence vocabulary only, no legal assessment; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_legal_evidence_literals_literal_index_snapshot_compare
POST /v1/baumarkt/media/clinical-appointment-literals-literal-index/snapshot-compare
Compare Timestamped source search for appointment vocabulary only, no medical assessment; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls.
0.031 USDC je Aufruf · MCP media_clinical_appointment_literals_literal_index_snap_67c48295
POST /v1/baumarkt/media/clinical-medication-literals-literal-index/snapshot-compare
Compare Timestamped source search for medication vocabulary only, no dose or clinical inference; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls.
0.031 USDC je Aufruf · MCP media_clinical_medication_literals_literal_index_snaps_18ab31ed
POST /v1/baumarkt/media/clinical-symptom-literals-literal-index/snapshot-compare
Compare Timestamped source search for symptom vocabulary only, no diagnostic claim; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_clinical_symptom_literals_literal_index_snapshot_compare
POST /v1/baumarkt/media/education-assessment-literal-index/snapshot-compare
Compare Timestamped source search for assessment planning wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_education_assessment_literal_index_snapshot_compare
POST /v1/baumarkt/media/education-curriculum-literal-index/snapshot-compare
Compare Timestamped source search for curriculum discussion wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_education_curriculum_literal_index_snapshot_compare
POST /v1/baumarkt/media/events-venue-literal-index/snapshot-compare
Compare Timestamped source search for venue planning wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_events_venue_literal_index_snapshot_compare
POST /v1/baumarkt/media/events-catering-literal-index/snapshot-compare
Compare Timestamped source search for catering planning wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_events_catering_literal_index_snapshot_compare
POST /v1/baumarkt/media/marketing-campaign-literal-index/snapshot-compare
Compare Timestamped source search for campaign discussion wording; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_marketing_campaign_literal_index_snapshot_compare
POST /v1/baumarkt/media/marketing-consent-literal-index/snapshot-compare
Compare Timestamped source search for consent vocabulary, no legal conclusion; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls. Full current provider disclosure retained; baseline is not submitted to the provider.
0.031 USDC je Aufruf · MCP media_marketing_consent_literal_index_snapshot_compare