YourAITools MCP Hub

Transcribe: Transcribe audio (speech-to-text)

transcribe_audio

Read-onlyIdempotent

Speech-to-text for a public MP3, WAV, M4A or OGG/Opus file (audio_url, up to 30 minutes / 30 MB): returns the transcript, detected language, timestamped segments and optional SRT/VTT subtitles (format=srt|vtt); task=translate returns English. Paid only, per started audio minute: the length is read before payment, so the terms quote the exact total. Charged only when a transcript is returned. Machine transcription can contain errors. Not for: FLAC or WebM (convert first).

[Transcribe via YourAITools MCP Hub] No free tier (paid route only). Paid: transcribe $0.003 per audio minute (rounded up, min 1), quoted exactly for your file before you pay, with a credits key (Authorization: Bearer yatc_...) or x402 (USDC; the hub returns the payment terms). Failed tool calls aren't charged: credits are refunded automatically and x402 payments only settle on success.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "audio_url": "<audio_url>"
    },
    "name": "transcribe_audio"
  }
}

Input Schema

Name	Required	Description
`vad`	No	Skip silence with voice activity detection (default false)
`task`	No	transcribe (default) or translate (to English)
`tier`	No	Paid tier: transcribe $0.003 per audio minute (rounded up, min 1). Default transcribe.
`format`	No	json (default); srt or vtt also returns subtitles in the srt / vtt field
`prompt`	No	Optional context words or spellings (max 500 chars)
`language`	No	Optional ISO 639-1 code of the spoken language (e.g. en, es, de); detected when omitted
`audio_url`	Yes	Public https URL of an MP3, WAV, M4A or OGG/Opus file (up to 30 minutes / 30 MB). Or POST the file as the raw body (e.g. Content-Type audio/mpeg, audio/wav, audio/mp4 or audio/ogg), or JSON audio_base64.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 30, 2026
- addedInput schema / properties / audio_url / examples
```
Added value: +[
+  "https://www.voiptroubleshooter.com/open_speech/american/OSR_us_000_0010_8k.wav"
+]
```
- addedInput schema / properties / format / examples
```
Added value: +[
+  "json"
+]
```

Changed1 schema field changedOct 27, 2026

changedInput schema / properties / audio_url / description

Previous value: -"Public https URL of an MP3 or WAV file (up to 30 minutes / 30 MB). Or POST the file as the raw body (Content-Type audio/mpeg or audio/wav), or JSON audio_base64."New value: +"Public https URL of an MP3, WAV, M4A or OGG/Opus file (up to 30 minutes / 30 MB). Or POST the file as the raw body (e.g. Content-Type audio/mpeg, audio/wav, audio/mp4 or audio/ogg), or JSON audio_base64."

AddedOct 25, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description adds real context on top: length is read before payment so the quote is exact, per-started-minute billing with a minimum, charge-on-success only, credits refunded on failure, x402 settlement only on success, and the caveat that transcription can contain errors. That is well beyond what the annotations convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded and dense: capabilities, limits, exclusions, then pricing. It runs long, and the '[Transcribe via YourAITools MCP Hub] No free tier (paid route only)' banner plus repetition of the per-minute rate (also restated in the tier schema) is padding, but little of the remainder is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-shot paid transcription call with no output schema, the description supplies everything an agent needs: accepted inputs and sizes, return payload, cost model, auth mechanism, and failure/refund semantics. Nothing material is left to guess.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds cross-parameter meaning the schema does not: the 30-minute/30 MB ceiling on audio_url, that format=srt|vtt produces subtitles, and that task=translate returns English. It does not add anything on prompt, language, or vad beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Speech-to-text for a public MP3, WAV, M4A or OGG/Opus file') and immediately enumerates what comes back (transcript, detected language, timestamped segments, optional SRT/VTT). No sibling in the list does transcription, so no differentiation is needed, and the scope is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit exclusion ('Not for: FLAC or WebM (convert first)') and clarifies translate mode, which is genuine when/when-not guidance. It stops short of naming an alternative for unsupported formats or of describing when to prefer language detection over an explicit language, so it is strong but not exhaustive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All YourAITools MCP Hub tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?