Labsco
ross-sec logo

kokoro-tts-mcp-server

from ross-sec

Model Context Protocol (MCP) server for Kokoro text-to-speech with female voice. 100% local, no Python required. Supports SSE and stdio transports.

πŸ”₯πŸ”₯πŸ”₯βœ“ VerifiedFreeNeeds API keys
<div align="center">

Ross Technologies Logo

MCP server for text-to-speech using Kokoro TTS

npm version License: MIT GitHub

100% Local β€’ No Python Required β€’ Female Voice Default

πŸ“¦ NPM Package | πŸ™ GitHub Repository | πŸ“š Documentation

</div>

Overview

A production-ready MCP server that provides text-to-speech capabilities using the Kokoro TTS model. Features a default female voice (af_heart) and runs 100% locally using native JavaScript, eliminating Python dependencies.

Built by Ross Technologies
πŸ“ Beer Sheva, Israel | πŸ“§ devops.ross@gmail.com

Features

βœ… 100% Local - No external API calls, complete privacy
βœ… Native JavaScript - Built with TypeScript and Node.js
βœ… SSE & Stdio Support - Multiple transport modes
βœ… NPX Ready - Run directly without installation
βœ… Female Voice Default - Uses af_heart voice out of the box
βœ… Auto Audio Playback - Automatically saves and plays generated audio

Documentation

πŸ“š Full Documentation Wiki

Quick Links:

Contributing

Contributions are welcome! See:

Links & Resources

License

MIT License - See LICENSE for details.

Copyright Β© 2025 Ross Technologies. All rights reserved.


<div align="center">

Made with ❀️ by Ross Technologies

Back to Top

</div>