Skip to main content
Glama

Speech to text, transcribe audio: Whisper transcription of an audio file

transcribe
Read-only

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, meeting snippets, subtitles and voice messages. Example: url=https://commons.wikimedia.org/wiki/Special:FilePath/En-us-hello.ogg. Price $0.01/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

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": {
      "url": "<url>"
    },
    "name": "transcribe"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesAbsolute 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 transcribes the short public sample shown in the example.
languageNoSpoken language code such as en, sv or de (default: detected)
subtitlesNosrt or vtt: also return subtitle text
timestampsNotrue: also return timed segments and words

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / url / description
      Previous value: -"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)"New value: +"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 transcribes the short public sample shown in the example."
  2. Changed4 schema fields changed
    • addedInput schema / properties / language
      Added value: +{
      +  "description": "Spoken language code such as en, sv or de (default: detected)",
      +  "type": "string"
      +}
    • addedInput schema / properties / subtitles
      Added value: +{
      +  "description": "srt or vtt: also return subtitle text",
      +  "type": "string"
      +}
    • addedInput schema / properties / timestamps
      Added value: +{
      +  "description": "true: also return timed segments and words",
      +  "type": [
      +    "string",
      +    "number",
      +    "boolean"
      +  ]
      +}
    • changedInput schema / properties / url / description
      Previous value: -"Absolute http(s) URL of an audio file (max 5 MB)"New value: +"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)"
  3. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Goes well past the annotations: discloses pricing ($0.01/call, failed calls free), why repeats cost money (reinforcing idempotentHint=false), accepted input paths (URL, POST body, multipart file, base64 JSON), the 5 MB cap, and 90+ language support. The 'reads or computes only and changes nothing' line corroborates readOnlyHint/destructiveHint rather than contradicting them.

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 with the action and model, then outputs, then parameters, then limits and pricing — a logical order with no filler. The pricing sentence is dense but justified because it explains the non-idempotent charging behavior.

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?

With no output schema, the description carries the return-value burden and does so fully: transcript text, detected language, duration, word count, plus conditional subtitles and timed segments. Input methods, size limit, language coverage and cost are all covered, leaving nothing an agent needs missing.

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 coverage is 100%, so the baseline is 3; the description restates the effects of subtitles=srt/vtt and timestamps=true at roughly the same fidelity the schema already provides. The only extra signal is the '90+ languages' scope for the language param, which is marginal added meaning.

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?

Names a specific verb and resource plus the underlying model ('Transcribe speech from an audio file ... using Whisper large-v3-turbo'), and the 5 MB ceiling implicitly separates it from longer-audio siblings like transcribe_long. It never names an alternative outright, so the differentiation is inferred rather than stated.

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?

Supplies concrete use cases ('voice notes, podcast clips, meeting snippets, subtitles and voice messages') and a worked example URL, which tells an agent when this tool fits. It stops short of when-not guidance or pointing to transcribe_speakers/transcribe_summary for those needs.

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.