koroko-speech-mcp
If you are the rightful owner of koroko-speech-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
A Model Context Protocol server that provides text-to-speech capabilities using the Kokoro TTS model.
The Speech MCP Server is a robust solution for converting text to speech using the Kokoro TTS model. It offers high-quality audio output with multiple voice options and customizable speech parameters such as speed and voice selection. The server is designed to be MCP-compliant, ensuring seamless integration with other MCP tools and services. It is easy to install and set up, requiring no API key, which makes it accessible for developers and users alike. The server can be configured using environment variables to set default speech speed and voice, providing flexibility in its operation. Additionally, it includes tools for listing available voices and checking the model's initialization status, which is particularly useful for monitoring and troubleshooting.
Features
- High-quality text-to-speech using Kokoro TTS model
- Multiple voice options available
- Customizable speech parameters (voice, speed)
- MCP-compliant interface
- Easy installation and setup
Tools
text_to_speech
Basic text-to-speech conversion
text_to_speech_with_options
Text-to-speech with customizable speed
list_voices
List all available voices
get_model_status
Check the initialization status of the TTS model
