SiliconFlow Voice Transcription MCP server

This MCP-Audio plugin provides voice-to-text transcription capabilities through the Audio speech recognition API, following the AIO-2030 compliance standards. It supports multiple input formats and returns structured outputs according to the JSON-RPC specification.

Installation

Local Setup

To install and run the MCP-Audio server locally:

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

Next, create and configure your environment file:

cp .env.example .env

Edit the .env file to include your API credentials:

AUDIO_URL=https--xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
API_KEY=sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

Start the MCP server:

python src/mcp_server.py

Docker Installation

Alternatively, you can run the server using Docker:

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

Usage

The MCP-Audio server provides several endpoints for voice transcription:

Direct Audio Upload

Send audio files directly to the server:

POST /api/v1/mcp/voice_model

This endpoint accepts .wav or .mp3 files using multipart/form-data and returns a JSON response:

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

AIO Protocol Integration

For integration with the AIO Protocol, use:

POST /api/v1/mcp/tools.call

This endpoint accepts JSON-RPC formatted requests with base64-encoded audio:

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

Help Documentation

To retrieve the service documentation:

GET /api/v1/mcp/help

This endpoint serves the contents of mcp_audio_registration.json, which can be used by Queen AI for MCP discovery and service indexing.

Testing

You can verify your installation using the included test scripts:

python test/test_audio_base64.py

To check if the server is running correctly:

python health_check.py

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.