概要
Koroko Speech is a Model Context Protocol (MCP) server delivering high-quality text-to-speech functionality powered by the Kokoro TTS model. It offers multiple voice options, customizable speech parameters like speed, and easy installation without requiring an API key. This server exposes tools for basic text-to-speech conversion, text-to-speech with options, voice listing, and model status checks, making it simple to integrate into MCP-compliant environments for versatile speech synthesis applications.
主な機能
- Multiple voice options available
- 1 GitHub stars
- Customizable speech parameters (voice, speed)
- MCP-compliant interface
- High-quality text-to-speech using Kokoro TTS model
- No API key required
ユースケース
- Integrating text-to-speech into MCP-compatible applications
- Automating voice generation for various tasks
- Adding speech capabilities to Claude Desktop
Sponsored