Skip to main content
Glama

Poly-Glot AI Workspace

by io.github.hmoses
OverviewDiscussionsAdmin

Transcribe audio

transcribe_audio

Convert audio to transcript text for Poly-Glot workflows. Use for supplied speech recordings, not for translating text. Provide exactly one source: a publicly reachable HTTPS audioUrl or base64-encoded audioBase64 (without a data-URL prefix). For base64 audio, supply mimeType and filename when known; languageHint can improve recognition. Set detectLanguage=true to identify the resulting text's language. Requires an active trial or Pro. Returns JSON containing transcript text, optional detectedLanguage, provider, and model. Audio is submitted to a transcription provider; do not send material without permission.

Input Schema

NameRequiredDescriptionDefault
promptNoOptional recognition context, such as expected names or specialist vocabulary; not the text to transcribe.
audioUrlNoPublic HTTPS URL of an audio recording to transcribe. Use this OR audioBase64, never both; private or local URLs are not supported.
filenameNoOriginal audio filename with extension, such as meeting.m4a, to help determine the format.
mimeTypeNoAudio MIME type, such as audio/mpeg, audio/mp4, or audio/wav. Recommended for base64 input.
audioBase64NoBase64-encoded audio bytes, without a data: prefix. Alternative to audioUrl; provide exactly one audio source.
languageHintNoOptional language hint for speech recognition, such as en, es, or fr. Leave blank if unknown.
detectLanguageNoWhen true, also infer a supported Poly-Glot language from the resulting transcript; defaults to false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changed
    • addedInput schema / properties / audioBase64 / description
      Added value: +"Base64-encoded audio bytes, without a data: prefix. Alternative to audioUrl; provide exactly one audio source."
    • addedInput schema / properties / audioUrl / description
      Added value: +"Public HTTPS URL of an audio recording to transcribe. Use this OR audioBase64, never both; private or local URLs are not supported."
    • addedInput schema / properties / detectLanguage / description
      Added value: +"When true, also infer a supported Poly-Glot language from the resulting transcript; defaults to false."
    • addedInput schema / properties / filename / description
      Added value: +"Original audio filename with extension, such as meeting.m4a, to help determine the format."
    • addedInput schema / properties / languageHint / description
      Added value: +"Optional language hint for speech recognition, such as en, es, or fr. Leave blank if unknown."
    • addedInput schema / properties / mimeType / description
      Added value: +"Audio MIME type, such as audio/mpeg, audio/mp4, or audio/wav. Recommended for base64 input."
    • addedInput schema / properties / prompt / description
      Added value: +"Optional recognition context, such as expected names or specialist vocabulary; not the text to transcribe."
  2. First observed

TDQS

A4.5/5.0
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 entitlement requirement ("Requires an active trial or Pro"), names the return payload fields, and warns that audio is submitted to a third-party provider. It omits size limits, failure modes, and latency/rate behavior, which keeps it short of a 5.

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?

The source constraint and the primary tool purpose are front-loaded, and each subsequent sentence carries distinct, actionable information (entitlement, inputs, return shape, privacy warning) without padding.

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?

For a 7-parameter tool with no output schema and no annotations, the description covers purpose, routing, input rules, entitlement, return contents, and a data-handling caveat. Nothing an agent needs to invoke it 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 description coverage is 100%, so parameters are already documented and the baseline is 3. The description reinforces the exactly-one-source constraint and the mimeType/filename conditional, but adds little syntax or format detail beyond what the schema states.

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+resource ("Convert audio to transcript text") and immediately scopes it against the sibling space with "Use for supplied speech recordings, not for translating text." An agent can distinguish this from translate_text/localize_text 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?

Explicit when-to-use (supplied speech recordings), when-not (translating text), and the selection rule for inputs ("Provide exactly one source"). It also names the alternative forms of input and their conditions, leaving little to inference.

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

All Poly-Glot AI Workspace 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