Edge Tts MCP Server

🚀 Edge-TTS MCP Server

A Model Context Protocol (MCP) server that uses Microsoft Edge's text-to-speech feature to provide speech synthesis services through AI agents.

🚀 Quick Start

This MCP server utilizes the edge-tts library to offer text-to-speech conversion capabilities. It aims to enable AI agents to respond with natural voices.

✨ Features

• Text-to-speech conversion
• Support for multiple voices and languages
• Adjustment of speech speed and pitch
• Audio streaming media

📦 Installation

You can install the server using pip:

pip install "edge_tts_mcp_server"

Or, for development mode:

git clone https://github.com/yuiseki/edge_tts_mcp_server.git
cd edge_tts_mcp_server
pip install -e .

💻 Usage Examples

Basic Usage

VS Code Configuration Example

Here is an example of configuring in VS Code's settings.json:

"mcp": {
  "servers": {
    "edge-tts": {
      "command": "uv",
      "args": [
        "--directory",
        "C:\\Users\\__username__\\src\\edge_tts_mcp_server\\src\\edge_tts_mcp_server",
        "run",
        "server.py"
      ]
    }
  }
}

Running with MCP Inspector

Run as a standard MCP server:

mcp dev server.py

Running with Uvicorn

When running the FastAPI-based server using uv:

uv --directory path/to/edge_tts_mcp_server/src/edge_tts_mcp_server run server.py

Command-line options:

edge-tts-mcp --host 0.0.0.0 --port 8080 --reload

📚 Documentation

API Endpoints

When running in FastAPI mode, you can use the following endpoints:

• / - API information
• /health - Health check
• /voices - List of available voices (optional parameter: ?locale=ja-JP for filtering)
• /mcp - MCP API endpoint

📄 License

This project is licensed under the MIT license.