MCP tool reference · #260 of 563 by publishers
transcribe_audio
Exposed by 12 servers from 12 publishers, read from the live servers by the Serverdex check; most of them sit in Media & Creative; 75% of them take a language parameter; the most-starred is Sats4AI - Bitcoin-Powered AI Tools (2 stars).
transcribe_audio(language?: string, url: string, audio_base64: string, …)Parameters
share = % of the 12 servers whose schema has it · required = % of those that mark it required| Parameter | Type | Share | Required | Usual description |
|---|---|---|---|---|
| language | string | 75% | 0% | Language of the recording, like 'en-US', 'de-DE', 'Arabic' or 'es', or 'auto' to detect it (default). Naming it is more accurate. |
| url | string | 33.3% | 75% | https link to an audio or video file (mp3, m4a, wav, mp4, webm …), up to 25 MB |
| audio_base64 | string | 25% | 100% | Base64-encoded audio bytes, without a data: prefix. |
| audio_url | string | 16.7% | 0% | Public http(s) URL of the audio to transcribe (<= 2048 chars). Required to start a new job; omit when polling with `job_id` only. |
| audioBase64 | string | 16.7% | 50% | Base64 encoded audio file |
| filename | string | 16.7% | 50% | Original audio filename with extension, such as meeting.m4a, to help determine the format. |
| speakers | boolean | 16.7% | 0% | Label who is speaking (Speaker 1, Speaker 2, up to 6). Default false. |
| timestamps | boolean | 16.7% | 0% | Start each line with its time, like [01:15]. Default false. |
| translate_to_english | boolean | 16.7% | 0% | Translate the speech into English instead of transcribing it as spoken. |
| audio_file | object | 8.3% | 0% | A file the user attached in the chat. |
| audio_format | — | 8.3% | 0% | Audio format hint — 'wav', 'mp3', 'ogg', 'flac', 'webm'. Auto-detected if omitted. |
| audioUrl | string | 8.3% | 0% | Public HTTPS URL of an audio recording to transcribe. Use this OR audioBase64, never both; private or local URLs are not supported. |
Source: the input schema each server returns for transcribe_audio, aggregated over the 12 index-tier servers; type and description are the values most servers use. Rebuilt every 6 hours.
Servers with transcribe_audio
12 of 12 · 12 publishers · 12 answering live · most-starred first, 3 per publisher| # | Server | Publisher | Category | ★ | Live | How it describes transcribe_audio |
|---|---|---|---|---|---|---|
| 1 | Sats4AI - Bitcoin-Powered AI Toolscnghockey · Communication | cnghockey | Communication | 2 | yes | Transcribe audio to text with WORD-LEVEL timestamps (timestamps:'word' returns per-word start/end times — subtitle alignment, karaoke captions, cutting video to speech) or segment timestamps. Uses Mistral Transcription — high-accuracy speech recognition that handles accents, background noise, and overlapping speakers. 13 languages: en, zh, hi, es, ar, fr, pt, ru, de, ja, ko, it, nl. Pass names (th |
| 2 | Embeddings, Rerank & Speech-to-Text (Tanod)tanod-labs · AI & Agents | tanod-labs | AI & Agents | 1 | yes | mlpeek: Speech to text and subtitles: transcribe audio to text, timed segments, SRT and WebVTT. For a podcast episode use transcribe_podcast_episode; to translate use translate_speech. Returns the transcript of audio of up to 10 min and 25 MB; `translate_to_english` gives English; `speakers` labels each segment's speaker; `chapters` adds titled chapters (start, title, gist). Too long, big or unrea |
| 3 | Nativnativ-technologies · Media & Creative | nativ-technologies | Media & Creative | 1 | yes | Transcribe speech from an audio or video file (unbilled draft). Use the returned segments with `translate` (origin via text) then `synthesize_audio` to produce a dubbed track. Video uploads also return a video_id for muxing. Args: file_path: Public HTTPS URL (hosted) or local path (stdio) to audio (mp3, wav, m4a, …) or video (mp4, mov, …). |
| 4 | Xenitionxenition · Media & Creative | xenition | Media & Creative | 1 | yes | Use this when the user wants the words from an audio or video recording — a meeting, lecture, interview or voice memo — and gives a link to the file (https, up to 25 MB). Returns the transcript and saves it as a document in their Xenition workspace. To turn it into notes and action items, pass the text to meeting_notes. |
| 5 | AIPayGendamien829 · Search & Web | damien829 | Search & Web | — | yes | Transcribe speech from an audio file URL (mp3, wav, m4a, ogg, webm; up to 20 MB) into text with timestamps, in 90+ languages with automatic language detection. Can also translate the speech into English. Good for podcasts, calls, voice notes and meetings. Costs $0.01 per call. |
| 6 | ImgKits MCPyichong1 · Media & Creative | yichong1 | Media & Creative | — | yes | Transcribe a public audio URL via Faster-Whisper (async create + result poll; no status endpoint). Pass `audio_url` (http(s)) to start or `job_id` to poll. Optional `language`, `response_format` (simple|raw). Empty transcript is still success (no speech detected). Cost: 2 credits per call. Compliance / SSRF: Use only on material you own or are explicitly licensed/authorized to generate or remix. D |
| 7 | Easy-Peasy.AIeasy-peasy-ai · Media & Creative | easy-peasy-ai | Media & Creative | — | yes | Transcribe audio or video from a public link: a media file, or a page with a video or audio in it — YouTube, X (Twitter) posts and broadcasts, Instagram, TikTok, Google Drive, SoundCloud, Loom and most other video sites (up to 6 hours). ASYNC — returns a uuid once the job has started (checking a page link can take up to a minute); then poll get_transcription until the transcript is ready, which ta |
| 8 | Justcaptionsspacesheepboy · Media & Creative | spacesheepboy | Media & Creative | — | yes | Transcribe extracted audio into segments and word timestamps. Max 12 MB decoded. Never send video. Charged by audio duration past the free allowance. |
| 9 | FreeTTSfreetts · Media & Creative | freetts | Media & Creative | — | yes | Turn a recording into text with FreeTTS speech to text (PRO). Give the audio as a file the user attached (audio_file) or a public https link to the file (audio_url): mp3, wav, m4a, ogg, flac, aac, webm, or a video file. Up to 200 MB and the plan's length per recording (PRO: 4 hours). Optional: speakers (label who speaks), timestamps (a time on every line), subtitles ('srt' or 'vtt' file). A long r |
| 10 | PyAI Voice AIatomsai · Media & Creative | atomsai | Media & Creative | — | yes | Transcribe a small audio attachment supplied as base64 (up to 8 MiB decoded). Returns the synchronous transcript without diarization controls. For word timestamps and speaker labels, use create_transcription_job with diarize=true for mono or channel=true for stereo, then get_transcription_job. Consumes usage. |
| 11 | Poly-Glot AI Workspacehmoses · Other | hmoses | Other | — | yes | Convert audio to transcript text for Poly-Glot workflows. Use for supplied speech recordings, not for translating text. Provide exactly one source: a publicly reachable HTTPS audioUrl or base64-encoded audioBase64 (without a data-URL prefix). For base64 audio, supply mimeType and filename when known; languageHint can improve recognition. Set detectLanguage=true to identify the resulting text's lan |
| 12 | Speech AI - Pronunciation, STT & TTSfasuizu-br · Media & Creative | fasuizu-br | Media & Creative | — | yes | Transcribe audio to text with word-level timestamps. Converts spoken English audio into text with optional word-level timestamps and per-word confidence scores. Args: audio_base64: Base64-encoded audio data (WAV, MP3, OGG, FLAC, WebM). audio_format: Audio format hint. Auto-detected from magic bytes if omitted. include_timestamps: Whether to include word-level timing (default: true). |
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.