Skip to main content
Glama

Transcription

transcribe
Read-only

Transcribe audio with speaker diarization and timestamps. Returns the full transcript with its confidence, language, duration, word and speaker counts, and the utterances, each with its speaker and start and end time. Use for meetings, interviews and podcasts, where who spoke when matters. For a short clip's word timings use stt; for caption files use subtitle. Cost: 3 credits, charged only when a call succeeds.

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"
  }
}

Input Schema

NameRequiredDescriptionDefault
languageNoLanguage code.en
audio_urlYesURL to audio/video file.
speaker_labelsNoEnable speaker diarization.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing the return payload (confidence, language, duration, word/speaker counts, utterances with speaker and start/end times) and a precise cost model: 3 credits charged only on successful calls. It leaves out failure modes and input limits (file size, URL accessibility), which keeps it short of a 5 given there is no output schema to lean on.

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

Conciseness5/5

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

Three sentences ordered by importance: capability, return shape, then sibling routing, closing with cost. No filler and nothing repeated from the title or annotations.

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 and only three simple parameters, the description carries the necessary burden by describing return values, the paid-cost condition, and the alternative tools. Nothing an agent needs to decide and call correctly is 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 language, audio_url and speaker_labels are already documented in the schema. The description reinforces that diarization and timestamps are outputs to expect and frames when speaker identification matters, but adds no format or syntax detail beyond that — the baseline 3 applies.

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 its distinguishing capability (speaker diarization and timestamps), and names the sibling tools it is not. An agent can distinguish it from stt and subtitle without consulting any schema.

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

Usage Guidelines5/5

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

Gives both when-to-use ('meetings, interviews and podcasts, where who spoke when matters') and explicit routing to alternatives — stt for a short clip's word timings, subtitle for caption files. Both exclusions are conditioned on concrete task properties.

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.