mcp-fish-audio-server
If you are the rightful owner of mcp-fish-audio-server 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.
Fish Audio MCP Server is a Model Context Protocol server that integrates Fish Audio's Text-to-Speech API with LLMs like Claude for natural language-driven speech synthesis.
The Fish Audio MCP Server is designed to provide seamless integration between Fish Audio's Text-to-Speech (TTS) API and large language models (LLMs) such as Claude. This server facilitates natural language-driven speech synthesis, allowing users to convert text into high-quality audio. It supports real-time audio streaming, multiple voice models, and various audio formats, making it suitable for a wide range of applications. The server is easy to configure using environment variables and can be integrated with Claude Desktop or any MCP client. With its flexible configuration options, users can customize voice models, output formats, and streaming settings to meet their specific needs. The server also includes robust error handling to manage common issues such as invalid API keys, network errors, and quota limits.
Features
- High-Quality TTS: Leverage Fish Audio's state-of-the-art TTS models.
- Streaming Support: Real-time audio streaming for low-latency applications.
- Multiple Voices: Support for custom voice models via reference IDs.
- Flexible Configuration: Environment variable-based configuration.
- Multiple Audio Formats: Support for MP3, WAV, PCM, and Opus.
Tools
fish_audio_tts
Generates speech from text using Fish Audio's TTS API.