Skip to main content
Glama

Audio Url Transcription

audio_url_transcription

Transcribe audio from Twitter Spaces URL to text using Whisper models.

Extracts and transcribes audio from Twitter Spaces URLs. NOTE: This endpoint only works with Twitter Spaces URLs. For video content, use video_url_transcription instead.


Available models:

  • WhisperLargeV3Ct2: ts_level: segment|word, diarize, output=json (text + segments)

  • WhisperLargeV3: ts_level: segment

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>",
      "include_ts": "<include_ts>"
    },
    "name": "audio_url_transcription"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoLanguage of the recording as an ISO code, e.g. 'en', 'pl'. Set it whenever you know the language: auto-detection can pick the wrong one, e.g. on short or accented audio. It forces the output language, so a wrong code returns a translation instead of a transcript. Auto-detected when unset
modelNoWhisper model from the model list. Default WhisperLargeV3Ct2: honours lang, returns segments, supports diarize and word timestampsWhisperLargeV3Ct2
diarizeNoLabel who is speaking; implies include_ts. Only on models marked 'diarize' in the model list (WhisperLargeV3 rejects it). Costs 1.5x, not stacked with a finer ts_level
ts_levelNoTimestamp granularity: 'segment', 'word' or 'char'; implies include_ts. Only the levels a model lists under 'ts_level' in the model list are accepted (WhisperLargeV3: segment only). Finer than segment costs 1.5x on models that price it
audio_urlYesURL of Twitter Spaces audio to transcribe (e.g., 'https://twitter.com/i/spaces/1nAKEERkeLbKL')
include_tsYesInclude timestamps in transcription
webhook_urlNoHTTPS URL for deAPI to call when this job finishes. Notifies your own systems; the tool still returns the result here
webhook_secretNo32-255 char key deAPI signs the callback with (HMAC-SHA256). Needs webhook_url. A secret given in chat stays in the transcript
include_metadataNoInclude source metadata in the result. Carries a flat surcharge on models that price it
return_result_in_responseNoReturn transcription inline. Set to False for large files to get download URL instead

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full disclosure burden. It does contribute the hard input-domain restriction and the model capability matrix (which model honours lang, supports diarize, or accepts a given ts_level), but it says nothing about authentication, cost mechanics, or synchronous-versus-async behavior, all of which matter for a 10-parameter paid compute endpoint.

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

Conciseness3/5

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

The opening two sentences are redundant restatements of each other ('Transcribe audio from Twitter Spaces URL to text' versus 'Extracts and transcribes audio from Twitter Spaces URLs'), and the model list is truncated mid-entry ('WhisperLargeV3: ts_level: segment' with no closing detail). The URL restriction and sibling routing are correctly front-loaded, but the block has clear waste and an incomplete tail.

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, so return values need no explanation, and the ten parameters are fully documented in the schema. The description fills the remaining gaps that matter most for selection and correct invocation: the Twitter Spaces-only restriction and which model supports which timestamp granularity and diarization. Cost and job-execution semantics are the notable omissions.

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%, which sets a baseline of 3, but the description adds real meaning: several schema descriptions defer to 'the model list' ('Only on models marked diarize in the model list', 'WhisperLargeV3: segment only'), and the description is where that model list with its per-model ts_level and diarize flags lives. That cross-reference is information the schema alone does not contain.

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?

The description leads with a specific verb and resource ('Transcribe audio from Twitter Spaces URL to text using Whisper models') and immediately scopes it to a single input domain. It also explicitly names the sibling it is not ('For video content, use video_url_transcription instead'), so an agent can distinguish it 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?

It states the positive condition (Twitter Spaces URLs only) and the negative condition (not video content), and routes to a named alternative, video_url_transcription. This is explicit when/when-not/alternative guidance rather than inferred usage.

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.