Fish Audio

Integrates with Fish Audio's API to generate high-quality speech from text with configurable voice models, audio formats, and real-time streaming for creating conversational applications and automated content narration.

This MCP server provides text-to-speech capabilities through Fish Audio's API, enabling AI assistants to generate high-quality speech from text with support for custom voice models and real-time streaming. Built by Daichi Okazaki using TypeScript with the official Fish Audio SDK, it offers two main tools: TTS generation with configurable voice references, audio formats (MP3, WAV, PCM, Opus), and streaming modes, plus voice reference listing for managing multiple voice models through ID, name, or tag selection. The implementation features both HTTP and WebSocket streaming for low-latency audio generation, automatic cross-platform audio playbook (macOS, Windows, Linux), real-time audio streaming with immediate playback, and flexible voice reference management supporting both single and multiple voice configurations, making it valuable for creating conversational AI applications, automated content narration, accessibility tools, and building AI assistants that need high-quality speech synthesis without manual Fish Audio dashboard interaction.