Skip to main content
Glama

Speech-to-Text

stt
Read-only

Transcribe audio to text with timestamps. Returns the transcript, its confidence, language and duration, and every word with its start and end time. Use for a short clip whose exact words and timings you need. For a long recording with several speakers use transcribe; for caption files use subtitle. Pass audio_url, or the audio itself as audio_base64. Cost: 2 credits, charged only when a call succeeds.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "stt"
  }
}

Input Schema

NameRequiredDescriptionDefault
languageNoLanguage code.en
audio_urlNoURL to audio file.
audio_base64NoBase64-encoded audio.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and destructiveHint=false, yet the description still adds real value: the return payload (transcript, confidence, language, duration, per-word start/end times) and a cost model ('2 credits, charged only when a call succeeds'). The only gap is that 'short clip' implies a length or size limit without ever stating it, so an agent cannot tell where the boundary is.

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 purpose → returns → routing → inputs → cost. Every sentence carries new information; no restatement of the title or name.

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?

There is no output schema, and the description compensates by enumerating the return fields, so an agent knows what comes back. Cost, input modalities, and routing are covered. The only missing piece is a concrete size or duration bound behind 'short clip', which is the one thing that would prevent a mis-invocation.

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 the either/or relationship between audio_url and audio_base64 ('Pass audio_url, or the audio itself as audio_base64'), which matters because required-parameters is 0 and the schema alone does not signal that one of the two is needed. The language parameter is not discussed, but its default is documented in-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 and resource ('Transcribe audio to text') plus the distinguishing output trait ('with timestamps'). The next sentence names the two siblings it is not (transcribe, subtitle), so an agent can route without opening a 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 an explicit positive case ('a short clip whose exact words and timings you need') and two explicit alternatives with their selecting conditions: long multi-speaker recordings → transcribe, caption files → subtitle. Nothing is left to inference.

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.