fish-speech-mcp

fish-speech-mcp

3.2

If you are the rightful owner of fish-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.

An MCP server for text-to-speech synthesis (TTS) for LLMs.

Fish-Speech-MCP is a Model Context Protocol (MCP) server designed to facilitate text-to-speech synthesis for Language Learning Models (LLMs). It integrates seamlessly with Dive and other MCP-compatible LLMs, providing a robust solution for converting text into speech. The server supports saving voice references, which can be used for future voice cloning tasks. Communication with the Optivus server is handled via Socket.IO, ensuring efficient data exchange. The server is configurable through environment variables, allowing users to specify the server URL. Fish-Speech-MCP is ideal for applications requiring dynamic speech synthesis and voice cloning capabilities.

Features

  • Text-to-Speech: Convert text to speech using FishSpeech.
  • Saving a Voice Reference: Save a voice reference for future voice cloning.
  • MCP Integration: Works with Dive and other MCP-compatible LLMs.

Tools

  1. text_to_speech

    Convert text to speech using FishSpeech.

  2. save_voice_reference

    Save a voice reference for future voice cloning.