What is Mcp Audio

mcp-audio is a versatile audio processing library designed for handling various audio tasks, including playback, recording, and manipulation of audio streams.

Use cases

Use cases for mcp-audio include creating interactive soundscapes in games, developing audio editing tools, implementing voice recording features in applications, and enhancing user experiences with sound effects.

How to use

To use mcp-audio, install the library via package managers like npm or pip, and then import it into your project. Follow the documentation for specific functions and examples to integrate audio features into your application.

Key features

Key features of mcp-audio include support for multiple audio formats, real-time audio processing, customizable audio effects, and a user-friendly API for developers.

Where to use

mcp-audio can be used in various fields such as game development, multimedia applications, audio editing software, and any project that requires audio manipulation.

MCP-Audio Plugin

mcp-audio is an AIO-2030 compliant MCP plugin that performs voice-to-text transcription using the Audio speech recognition API.

It exposes the identify_voice method via both multipart/form-data and base64 formats, supports the AIO tools.call protocol, and returns JSON-RPC structured outputs.

Features

• Fully AIO-compliant MCP plugin (/tools.call, /help)
• Converts .wav/.mp3 audio files to transcripts using SiliconFlow
• API key managed securely via .env file
• Docker-compatible and minimal dependencies
• Registration-ready for AIO endpoint registry

Setup (Local)

1. Clone and Install

git clone [email protected]:AIO-2030/mcp-audio.git
cd mcp-audio
python -m venv venv && source venv/bin/activate
pip install -r requirements.txt

2. Add .env file

cp .env.example .env

Set your audio URL and API key:

AUDIO_URL=https--xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
API_KEY=sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

3. Run the MCP server

python src/mcp_server.py

4. Docker

4.1 Build and Run

docker build -t mcp-audio .
docker run --env-file .env -p 8080:8080 mcp-audio

API Overview

POST /api/v1/mcp/voice_model

Upload audio file directly. Response:

{
  "transcript": "hello world",
  "confidence": 0.91,
  "audio_hash": "a1b2c3..."
}

POST /api/v1/mcp/tools.call (AIO Protocol)

JSON-RPC format with base64-encoded audio. Response:

{
  "method": "tools.call",
  "params": {
    "method": "identify_voice",
    "inputs": [
      {
        "type": "audio",
        "value": "<base64-audio>"
      }
    ]
  }
}

GET /api/v1/mcp/help

Auto-serves contents of mcp_audio_registration.json. Used by Queen AI for MCP discovery and service indexing.

Testing Tools

Base64 Voice Test

python test/test_audio_base64.py

Health Check

python health_check.py

MCP Registration (to AIO Endpoint Canister)

./register_mcp.sh

Requires jq, dfx, and a running endpoint_registry canister.