Home / MCP / Edge-TTS MCP Server

Edge-TTS MCP Server

Provides edge-tts based text-to-speech synthesis for MCP clients with support for multiple voices, languages, and streaming audio.

python

5stars

View on GitHub

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
    "mcpServers": {
        "edge_tts": {
            "command": "uv",
            "args": [
                "--directory",
                "path/to/edge_tts_mcp_server/src/edge_tts_mcp_server",
                "run",
                "server.py"
            ]
        }
    }
}

You can run the Edge-TTS MCP Server to provide high-quality text-to-speech synthesis for AI agents. Built with the edge-tts library, this server lets you generate natural speech in multiple voices and languages, stream audio data, and adjust speaking speed and pitch for realistic interactions.

How to use

Start the MCP server locally and connect with your MCP client to request speech synthesis. You can run the server in a development-friendly way and then send text-to-speech requests through the MCP API endpoints. Typical usage flows involve starting the server, listing available voices, and then issuing synthesis requests for your AI agent responses.

How to install

Prerequisites: you need Python and a compatible package manager installed on your system.

Install the MCP server package from PyPI or use development mode for active development.

pip install "edge_tts_mcp_server"
```

```bash
# Development mode
git clone https://github.com/yuiseki/edge_tts_mcp_server.git
cd edge_tts_mcp_server
pip install -e .

Additional content

Usage examples and configuration details help you get started quickly.

Available tools

voice_synthesis

Converts input text to speech using edge-tts and returns audio data that can be streamed to clients.

list_voices

Retrieves the list of available voices and locales to tailor speech output to user preferences.

health_check

Provides a health status endpoint to verify the MCP server is running and ready to serve requests.

api_info

Returns information about supported endpoints and capabilities of the MCP server.