Overview
What is Edge-TTS MCP Server?
A Model Context Protocol (MCP) server that provides text-to-speech synthesis for AI agents using Microsoft Edge's text-to-speech engine. It leverages the edge-tts library to convert text into natural-sounding speech, designed to enable AI agents to respond audibly.
How to use Edge-TTS MCP Server?
Install the package via pip: pip install edge_tts_mcp_server. Configure the server in VS Code’s settings.json by specifying the command (uv) and path to the server.py file, or run directly using mcp dev server.py. Additional options include running with uv for FastAPI mode or using the CLI command edge-tts-mcp --host 0.0.0.0 --port 8080 --reload.
Key features of Edge-TTS MCP Server
- Text-to-speech conversion from arbitrary text.
- Support for multiple voices and languages.
- Adjustable speech speed and pitch.
- Audio data streaming capability.
Use cases of Edge-TTS MCP Server
—
FAQ from Edge-TTS MCP Server
How do I install Edge-TTS MCP Server?
Install via pip: pip install edge_tts_mcp_server. For development, clone the repository and run pip install -e ..
How can I configure Edge-TTS MCP Server in VS Code?
Add the server to your VS Code settings.json with the command uv and arguments pointing to the server.py file, as shown in the README example.
What API endpoints are available in FastAPI mode?
Endpoints include / (API info), /health (health check), /voices (list voices, optionally filtered by ?locale=ja-JP), and /mcp (MCP API endpoint).
Can I adjust the voice speed and pitch?
Yes, the server supports adjusting both the speed and pitch of the generated speech.
