Skip to main content
Glama

Agent Data Tools: Speech to text and text to speech

Speaker labels: transcribe audio with who said what (diarization)

transcribe_speakers
Read-only

Transcribe a meeting, interview, call or podcast with speaker labels: each turn says which speaker talked, with start and end times (Deepgram Nova-3). MP3/WAV up to 15 minutes, other formats up to 2 MB, by URL or upload. Optional redaction of personal data (pii), card numbers (pci) or numbers, and subtitles with the speaker in each line. Use for meeting minutes, interview transcripts, call reviews and podcast show notes. Example: url=https://upload.wikimedia.org/wikipedia/commons/7/77/Tofino_pronunciation.mp3. Price $0.10/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_speakers"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesAbsolute http(s) URL of the recording (MP3/WAV up to 15 minutes; M4A, OGG, WebM or FLAC up to 2 MB); or POST the file itself (raw body, multipart `file` part, or base64 in JSON)
redactNopii (names, addresses, phone numbers and other personal data), pci (card numbers) or numbers: replaced in the transcript
languageNoSpoken language code such as en, es, de or fr (default: detected)
subtitlesNosrt or vtt: also return subtitles, each line starting with its speaker

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior5/5

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

Goes well beyond the annotations by disclosing cost ($0.10/call via x402 USDC or card key, failed calls free), the fact that repeats are billed (reinforcing idempotentHint=false), and hard input limits. The 'reads or computes only and changes nothing' line matches readOnlyHint rather than contradicting it.

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-loads the core purpose and constraints in the first two sentences, with usage contexts, example and pricing following. It is dense but every clause carries information; only the redaction/subtitles restatement is redundant with the schema.

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

Completeness4/5

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

With no output schema, the description usefully sketches the return shape (turns with speaker and timestamps, optional subtitles with speaker prefixes) and covers limits and billing. It leaves return-container details and error behavior unstated, which is a minor gap for a paid transcription call.

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 schema already defines url, redact, language and subtitles in detail. The description restates the redaction modes and subtitle behavior with little added meaning, though the worked example URL for the required parameter is mildly useful. Baseline 3 is appropriate.

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 and resource (transcribe audio) plus the distinguishing capability: speaker labels/diarization with per-turn start and end times. The title and first sentence make it clearly different from a plain transcription sibling, and the named engine (Deepgram Nova-3) and input constraints further pin down the scope.

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 concrete usage contexts (meeting minutes, interview transcripts, call reviews, podcast show notes) and implicit boundaries via the 15-minute / 2 MB limits. It does not explicitly route the agent away from alternatives such as transcribe or transcribe_long when speaker labels are unneeded or the file is longer, so it stops short of full when/when-not guidance.

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.