VoiceStudio MCP

Official

Overview Schema Source Related Servers Discussions Admin

transcribe

Convert spoken audio into written text from a file path or base64 input, with optional language hint. Returns recognized text, detected language, and duration.

Instructions

Transcribe spoken audio to text.

    Pass exactly one of audio_base64 or audio_path.

    Args:
        audio_base64: Base64-encoded audio bytes (wav/mp3/webm/m4a).
        audio_path: Path to an audio file under OMNIVOICE_MCP_BASE_PATH
            (relative to it, or absolute inside it). The base path is the
            security boundary: with none configured, paths are refused.
            Prefer this lane for LLM agents - the audio never enters the
            agent's context.
        language: Optional language hint; omit for auto-detect.

    Returns:
        JSON with the recognized text, language, and duration.
     For long operations use voicestudio_start_job.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`language`	No
`audio_path`	No
`audio_base64`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 3, 2026

TDQS

A4.7/5.0

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 OMNIVOICE_MCP_BASE_PATH security boundary, that paths are refused when no base path is configured, and that the path lane keeps audio out of the agent's context. It omits auth/permission requirements and size or rate limits, so it falls 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.

Conciseness4/5

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

Front-loaded with the purpose and the one-of constraint, then organized into Args/Returns sections with no filler sentences. Slight redundancy in restating the return payload despite an output schema existing, and the docstring formatting is heavier than strictly necessary.

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 three-parameter tool with an output schema already covering return values, the description supplies everything else an agent needs: purpose, parameter constraints, the security boundary for file paths, and the escalation path to a job-based tool. No meaningful gap remains.

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?

Schema description coverage is 0%, so the description must compensate, and it does: each of the three params is explained with accepted formats (wav/mp3/webm/m4a), path resolution semantics relative to the base path, and the mutual-exclusivity constraint that the schema does not encode. Language is documented as an optional auto-detect hint.

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 ('Transcribe spoken audio to text') that an agent can distinguish from generate_speech and the voicestudio_* job tools. It also names voicestudio_start_job as the alternative for long operations, so the tool's niche is unambiguous.

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?

Gives an explicit selection rule ('Pass exactly one of audio_base64 or audio_path'), a preference recommendation for LLM agents (path lane, because audio never enters context), and a routing rule to voicestudio_start_job for long operations. This is when-to-use plus alternatives, not inference.

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