Agent Tools

audio_transcribe

Speech to text: transcribe an audio file at a URL (MP3, WAV, M4A/AAC, OGG/Opus, FLAC, WebM; max 10 MB) with Whisper large v3 turbo. Returns full text, detected language, duration, timestamped segments and WebVTT captions. task=translate gives English text. For podcasts, voice notes, calls and meetings. Price $0.02 USDC per call via x402. Example output: {"text":"Hello and welcome to the show.","language":"en","duration_seconds":4.2,"task":"transcribe","format":"mp3","bytes":67000,"word_count":6,"segments":[{"start":0,"end":4.2,"text":"Hello and welcome to the show."}],"model":"whisper-large-v3-turbo"}

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": "audio_transcribe"
  }
}

Input Schema

Name	Required	Description
`url`	Yes	Public URL of the media file itself
`vad`	No	true to apply voice activity filtering
`task`	No
`language`	No	Optional ISO code, e.g. en

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 31, 2026

TDQS

A4.3/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the 10 MB size cap, the $0.02 USDC per-call x402 payment, the model used, and the exact response fields. It omits error behavior, latency, and how x402 payment is actually settled, which are the remaining gaps.

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 core verb and resource, then formats, limits, price, and a sample response, with each sentence carrying information. The inline example output is long but directly substitutes for a missing output 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?

For a 4-parameter, no-annotation, no-output-schema tool, the description supplies formats, size limits, price, translate behavior, and a concrete response example. Only payment mechanics and failure modes are unaddressed.

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 75%, so the baseline is 3; the description adds real value by explaining that task=translate yields English text and by constraining url to supported audio formats under 10 MB. The vad parameter and the language ISO code are left entirely to the schema, so it does not fully compensate.

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 (transcribe) and resource (audio file at a URL), and the 'audio' framing plus format list naturally distinguishes it from the sibling video_transcribe. The model, supported formats, and output shape are all named, so an agent can identify the tool without opening the schema.

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?

Names concrete use cases (podcasts, voice notes, calls, meetings) and explains the task=translate variant gives English text, which is clear situational guidance. It stops short of explicit when-not conditions or a named alternative (e.g. video_transcribe for video inputs).

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

All Agent Tools tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?