fish-speech-mcp

fish-speech-mcp

1

Fish-speech-mcp is an MCP server designed to provide text-to-speech synthesis capabilities for large language models (LLMs). It allows users to convert text into speech and save voice references for future use. The server integrates with Dive and other MCP-compatible LLMs, offering enhanced text-to-speech functionalities.

fish-speech-mcp

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

Features

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

Installation

  • Add the MCP server via Dive Desktop

Configuration

  • Configurable via environment variables, e.g., MCP_FISH_SPEECH_SERVER_URL

Tool Documentation

  • text_to_speech: Converts text to speech
  • save_voice_reference: Saves a voice reference for voice cloning