ofaudio-mcp

transcribe

Convert speech to text from local audio/video files or URLs. Optional speaker diarization and subtitle files for podcasts, meetings, captions, and dubbing.

Instructions

Transcribe speech to text (ElevenLabs Scribe) — for podcasts, meetings, captions, dubbing prep.

Args: audio: A local audio/video file path, OR a URL (hosted file, YouTube, TikTok). language: ISO code (639-1 or -3) to force; omit to auto-detect. diarize: True to label speakers (who said what). captions: "srt" or "vtt" to also write a subtitle file (from word timings) and return its path.

Returns: {"text", "language_code", "words": , "captions_path"?} or {"error"}.

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": "<audio>"
    },
    "name": "transcribe"
  }
}

Input Schema

Name	Required	Description	Default
`audio`	Yes
`diarize`	No
`captions`	No
`language`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Jul 31, 2026

TDQS

A4.8/5.0

Behavior5/5

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

With no annotations provided, the description carries the full burden and excels: it discloses input types (local file/URL), optional behaviors (language forcing, diarization, caption file generation), and the exact return format including an error case. This is rich behavioral detail beyond a simple one-liner.

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 description is well-structured with a purpose line, Args, and Returns sections. Every line provides actionable information without fluff, making it easy to scan while remaining complete.

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?

Given the tool's complexity (4 parameters, optional captions output), the description covers all inputs, behaviors, and return values. The optional captions_path is explained, and the error return is acknowledged, making the description self-contained despite the lack of an output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds substantial meaning to every parameter: audio accepts a local path or URLs including YouTube/TikTok, language is an ISO code with auto-detect default, diarize labels speakers, and captions accepts 'srt' or 'vtt' and returns a path. This fully compensates for the 0% schema description coverage.

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 clearly states the tool's verb and resource: 'Transcribe speech to text' using ElevenLabs Scribe. It also lists concrete use cases (podcasts, meetings, captions, dubbing prep) that distinguish it from sibling tools like forced_alignment or generate_speech.

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?

Provides clear use-case context ('for podcasts, meetings, captions, dubbing prep') and explains when options like diarize or captions should be enabled. However, it does not explicitly name alternative tools or state when NOT to use this tool, so it stops short of full exclusionary guidance.

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