Skip to main content
Glama
Sign In

Gravity

by app.gravitynotes
OverviewDiscussionsAdmin

Transcribe a recording

transcribe_audio
Read-onlyIdempotent

Turn speech in a recording into text, in 99 languages. The audio is transcribed by AssemblyAI. A tag spoken first with a pause ("To do, call the bank") comes back written ("todo: call the bank"). To save it as a note in one step, use add_voice_note.

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": "transcribe_audio"
  }
}

Input Schema

NameRequiredDescriptionDefault
keywordsNoNames or rare words in the recording, spelled as they should be written.
languageNoThe spoken language as a code, e.g. en, de, ja. Leave out to detect it.
audio_urlNoAn https link to the recording (WAV, M4A, MP3, FLAC, OGG, WebM and most other audio or video formats).
upload_idNoThe upload_id from upload_audio, once the file has been PUT to its upload_url.
audio_base64NoThe recording itself, base64-encoded, up to 2 MB (a few minutes of compressed audio). For a larger file, use upload_audio and pass upload_id.

Output Schema

NameRequiredDescriptionDefault
textYesWhat was said. Empty when no speech was heard.
secondsYesLength of the recording.
languageYesDetected language code, e.g. en.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: transcription is delegated to a third-party provider (AssemblyAI), and spoken tag words with a pause are normalized into written prefixes, which an agent could not infer from structured fields.

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?

Four short sentences, each earning its place: purpose, provider, formatting quirk, and alternative routing. The core purpose is front-loaded and nothing is padded.

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?

An output schema exists and annotations are rich, so the description needn't explain return values. It covers the non-obvious behaviors and the main alternative; only the upload-then-transcribe workflow is left implicit, and the schema covers that.

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 description coverage is 100%, so all five parameters (keywords, language, audio_url, upload_id, audio_base64) are already documented in the schema itself. The description adds no parameter-level meaning, so the baseline of 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 ('Turn speech in a recording into text') plus scope ('99 languages'), and explicitly contrasts itself with the sibling add_voice_note, which saves a note in one step. An agent can tell it apart from add_voice_note or upload_audio without opening either 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?

Gives clear routing guidance: use add_voice_note when the goal is a note in one step, implying this tool is the bare transcription primitive. It does not spell out when-not to use it (e.g. that audio must already be uploaded or inlined), leaving that to the schema.

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

All Gravity toolsInspect
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