# Fish Audio

> Use this tool when you need to generate high-quality speech from text for conversational AI applications, automated content narration, or accessibility tools. It provides text-to-speech capabilities with support for custom voice models, real-time streaming, and configurable audio formats. The tool accepts text input and outputs audio in various formats, including MP3, WAV, PCM, and Opus, making it ideal for building AI assistants that require seamless speech synthesis.

Canonical page: https://skillsregistry.net/skills/fish-audio  
JSON: https://api.skillsregistry.net/v1/skills/fish-audio

## Description

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.

## Trust

- **Trust score (0–1):** 0.97
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/fish-audio)
- **Repository:** <https://github.com/da-okazaki/mcp-fish-audio-server>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "fish-audio"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/fish-audio` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/fish-audio/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt