MCP tool reference · #553 of 563 by publishers
transcribe
Exposed by 15 servers from 8 publishers, read from the live servers by the Serverdex check; most of them sit in Media & Creative; 86.7% of them take a language parameter; the most-starred is Agent Data Tools: Speech to text and text to speech (1 stars).
transcribe(language?: string, audio_url: string, url: string, model: string, prompt?: string, …)Parameters
share = % of the 15 servers whose schema has it · required = % of those that mark it required| Parameter | Type | Share | Required | Usual description |
|---|---|---|---|---|
| language | string | 86.7% | 0% | The spoken language as an ISO-639-1 code (en, es, zh...), when known. |
| audio_url | string | 46.7% | 100% | An https URL of the audio or video file: mp3, mp4, m4a, wav, webm, ogg, flac or aac, 25 MB at most. A file generate made works. |
| url | string | 40% | 83.3% | Absolute http(s) URL of an audio file (max 5 MB); or POST the file itself (raw body, multipart `file` part, or base64 in JSON). With no input at all this transc |
| model | string | 33.3% | 100% | A transcription model id from list_models (type transcription). |
| prompt | string | 33.3% | 0% | Names or words to spell right, or the text that came before. |
| timestamps | string | number | boolean | 33.3% | 0% | true: also return timed segments and words |
| translate | boolean | 33.3% | 0% | True: translate the speech into English instead (the models that can). |
| subtitles | string | 26.7% | 0% | srt or vtt: also return subtitle text |
| archivo_b64 | string | 6.7% | 100% | Audio en base64 (o subir 'archivo' por multipart) |
| audio_base64 | string | 6.7% | 0% | Alternative to url |
| diarize | boolean | 6.7% | 0% | Label speakers in `words` as `speaker_0`, `speaker_1`, … in order of first appearance. Default false. |
| filename | string | 6.7% | 0% | Filename with extension (e.g. "podcast.mp3"). Required on the first call — used to infer media type (audio vs video) and label outputs. Supported extensions: mp |
Source: the input schema each server returns for transcribe, aggregated over the 15 index-tier servers; type and description are the values most servers use. Rebuilt every 6 hours.
Servers with transcribe
12 of 15 · 8 publishers · 12 answering live · most-starred first, 3 per publisher| # | Server | Publisher | Category | ★ | Live | How it describes transcribe |
|---|---|---|---|---|---|---|
| 1 | Agent Data Tools: Speech to text and text to speechnutshell2000 · Media & Creative | nutshell2000 | Media & Creative | 1 | yes | Transcribe speech from an audio file at a public URL, or uploaded in a POST body, using Whisper large-v3-turbo. Returns the transcript text, detected language, duration and word count; subtitles=srt or vtt adds subtitle text and timestamps=true adds timed segments and words. Accepts common formats such as MP3, WAV, M4A and OGG up to 5 MB, in 90+ languages. Use for voice notes, podcast clips, meeti |
| 2 | Agent Data Tools: Full list (every tool as its own definition)nutshell2000 · Documents & Knowledge | nutshell2000 | Documents & Knowledge | 1 | yes | Transcribe speech from an audio file at a public URL, or uploaded in a POST body, using Whisper large-v3-turbo. Returns the transcript text, detected language, duration and word count; subtitles=srt or vtt adds subtitle text and timestamps=true adds timed segments and words. Accepts common formats such as MP3, WAV, M4A and OGG up to 5 MB, in 90+ languages. Use for voice notes, podcast clips, meeti |
| 3 | Agent Data Tools: AInutshell2000 · AI & Agents | nutshell2000 | AI & Agents | 1 | yes | Transcribe speech from an audio file at a public URL, or uploaded in a POST body, using Whisper large-v3-turbo. Returns the transcript text, detected language, duration and word count; subtitles=srt or vtt adds subtitle text and timestamps=true adds timed segments and words. Accepts common formats such as MP3, WAV, M4A and OGG up to 5 MB, in 90+ languages. Use for voice notes, podcast clips, meeti |
| 4 | Helvehelve-dev · APIs & Integrations | helve-dev | APIs & Integrations | — | yes | Submit a prerecorded audio or video URL for durable batch transcription. Returns immediately with a job ID; use transcription_status to retrieve its state and completed result. |
| 5 | PentestLLMuplinkswitch · Security & Identity | uplinkswitch | Security & Identity | — | yes | Turns the speech in an audio or video file at an https URL (25 MB at most; a file generate made works) into text through POST /v1/audio/transcriptions, or into English with translate. Use a transcription model id from list_models (type transcription). Billed per second of audio to the key in the MCP request's Authorization header; a request that fails is not charged. |
| 6 | Unrestrictableuplinkswitch · AI & Agents | uplinkswitch | AI & Agents | — | yes | Turns the speech in an audio or video file at an https URL (25 MB at most; a file generate made works) into text through POST /v1/audio/transcriptions, or into English with translate. Use a transcription model id from list_models (type transcription). Billed per second of audio to the key in the MCP request's Authorization header; a request that fails is not charged. |
| 7 | RelaySwitchuplinkswitch · Developer Tools | uplinkswitch | Developer Tools | — | yes | Turns the speech in an audio or video file at an https URL (25 MB at most; a file generate made works) into text through POST /v1/audio/transcriptions, or into English with translate. Use a transcription model id from list_models (type transcription). Billed per second of audio to the key in the MCP request's Authorization header; a request that fails is not charged. |
| 8 | Patchwellaidan-mccollum · Data & Analytics | aidan-mccollum | Data & Analytics | — | yes | Transcribe speech in an audio or video file. Use it when you need the words in a recording, quotes with their time, who said what, or subtitles. Returns text, sentence segments, each word with start/end seconds, confidence and speaker (`spk`: 1, 2, ... told apart by voice), `turns` (speaker, start, end, text), `speakers` with talk time (and a `name` with its supporting quot |
| 9 | Suprsonico-mega-enterprise · Other | o-mega-enterprise | Other | — | yes | Transcribe audio with speaker diarization and timestamps. Returns the full transcript with its confidence, language, duration, word and speaker counts, and the utterances, each with its speaker and start and end time. Use for meetings, interviews and podcasts, where who spoke when matters. For a short clip's word timings use stt; for caption files use subtitle. Cost: 3 credits, charged only when a |
| 10 | SiteCheckbck-stack · Crypto & Web3 | bck-stack | Crypto & Web3 | — | yes | Speech-to-text with Whisper large-v3-turbo: send an https audio URL (or base64) up to 10 minutes and 25 MB, get the transcript, language and timestamped segments. Usually takes about 17 s, up to 31 s on slower calls; allow a 60 s timeout. Price: $0.01 per successful call, paid with x402 (USDC on Base, Solana and 10 more networks); failed calls are not charged. |
| 11 | Andreaxmoralito311-andr · APIs & Integrations | moralito311-andr | APIs & Integrations | — | yes | Transcribe an audio file to text (speech-to-text) with LOCAL Whisper, automatic language detection. For agents processing voice notes, calls or podcasts. Upload the audio via multipart or as 'archivo_b64'. Optional 'lang' (es|en|...). [x402: 0.01 USDC on Base, pay-per-use] |
| 12 | Weftlywoven-record-media · Media & Creative | woven-record-media | Media & Creative | — | yes | Transcribe audio or video to text, including per-word timestamps for precise editing. Three-call flow: (1) call with `filename` to receive {job_id, payment_challenge}; (2) pay via MPP, then call with `job_id` + `payment_credential` to receive {upload_url} (presigned PUT, 1h expiry); (3) PUT the bytes, then complete_upload(job_id), then poll get_job_status(job_id). On completion, get_job_status ret |
Stars from GitHub as stored in the Serverdex index (re-read every 7 days per server); live = answered the last daily check of its hosted endpoint. The other 3 servers are reached from their publisher pages.