edge_tts_mcp_server

# Edge-TTS MCP Server Model Context Protocol (MCP) server that provides a speech synthesis service for AI agents using Microsoft Edge's text-to-speech capabilities. ## Overview This MCP server uses the [edge-tts](https://github.com/rany2/edge-tts) library to provide text-to-speech conversion. It is designed as a tool to enable AI agents to respond with natural-sounding voices. ## Features - Text-to-speech conversion - Support for multiple voices and languages - Adjustment of speech rate and pitch - Streaming of speech data ## Installation ```bash pip install "edge_tts_mcp_server" ``` Or install in development mode: ```bash git clone https://github.com/yuiseki/edge_tts_mcp_server.git cd edge_tts_mcp_server pip install -e . ``` ## Usage ### Example Configuration in VS Code Example configuration in VS Code's settings.json: ```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" ] } } } ``` ### Usage with MCP Inspector Run as a standard MCP server: ```bash mcp dev server.py ``` ### Running with uvx (uvicorn) Run as a FastAPI-based server with uv: ```bash uv --directory path/to/edge_tts_mcp_server/src/edge_tts_mcp_server run server.py ``` Command-line options: ```bash edge-tts-mcp --host 0.0.0.0 --port 8080 --reload ``` ## API Endpoints When running in FastAPI mode, the following endpoints are available: - `/` - API information - `/health` - Health check - `/voices` - List of available voices (optional filtering with `?locale=ja-JP`, etc.) - `/mcp` - MCP API endpoint ## License MIT