Skip to main content
Glama

Transcribe audio or video

transcribe
Read-onlyIdempotent

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.

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": {
      "model": "<model>",
      "audio_url": "<audio_url>"
    },
    "name": "transcribe"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelYesA transcription model id from list_models (type transcription).
promptNoNames or words to spell right, or the text that came before.
languageNoThe spoken language as an ISO-639-1 code (en, es, zh...), when known.
audio_urlYesAn 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.
translateNoTrue: translate the speech into English instead (the models that can).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds genuinely useful behavior beyond them: billing per second of audio charged to the key in the MCP request's Authorization header, and the fact that failed requests are not charged. It also discloses the 25 MB ceiling and accepted formats. It stops short of covering latency, rate limits, or the shape of the returned transcript.

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?

Two sentences, front-loaded with the core operation and followed by the billing caveat. Some wording is awkward and duplicative of the schema ('a file generate made works', the repeated 25 MB limit), but nothing is truly wasted.

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

Completeness3/5

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

With no output schema, the description should say what comes back — raw transcript text, JSON, timestamps, or a file reference — and it does not. Cost behavior and input constraints are well covered, so the main gap is the return contract for a tool an agent must chain from.

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

Parameters3/5

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

Schema description coverage is 100%, so all five parameters are already documented in structured form; the baseline is therefore 3. The description reinforces the model-source and translate semantics and the URL size/format constraints, but adds little that the schema does not already say about prompt or language.

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

Purpose4/5

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

States a specific verb and resource: it turns speech in an audio/video file at an https URL into text, with an English-translation mode. The endpoint POST /v1/audio/transcriptions pins the operation precisely. Sibling differentiation is only indirect (it points to list_models for model ids and mentions generate as an input source), so it falls short of a 5.

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

Usage Guidelines3/5

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

It gives a prerequisite (use a transcription model id from list_models, type transcription) and explains the translate flag as a mode choice. There is no explicit when-to-use/when-not guidance against other tools, and no statement of what to do if the file is over 25 MB or in an unsupported format.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.