koroko-speech-mcp

koroko-speech-mcp

0
communication

The Speech MCP Server provides text-to-speech capabilities through a Model Context Protocol interface, utilizing the Kokoro TTS model. It is highly customizable, supports multiple voices, and requires no API key, simplifying setup and usage.

Overview

Speech MCP Server is a Model Context Protocol server offering text-to-speech capabilities using the Kokoro TTS model. Key features include:

  • High-quality text-to-speech
  • Multiple voice options
  • Customizable speech parameters (voice, speed)
  • MCP-compliant interface
  • Easy installation
  • No API key required

Installation

  • Using npm: npm install speech-mcp-server
  • Using pnpm: pnpm add speech-mcp-server
  • Using yarn: yarn add speech-mcp-server

Usage

Run the server with default or custom configurations.

Tools

  • text_to_speech: Converts text to speech.
  • text_to_speech_with_options: Customizable text-to-speech.
  • list_voices: Lists all available voices.
  • get_model_status: Checks the status of TTS model initialization.

Contributing

Contributions are welcome via Pull Requests.

License

MIT License.