​
Overview

Integrate Fish Audio’s comprehensive documentation directly into your AI coding assistants. Using MCP (Model Context Protocol), coding agents like Claude Code, Cursor, and Windsurf can access our latest API references, guides, and examples in real-time.
The Fish Audio MCP server provides instant access to:
  • Complete API documentation
  • SDK usage examples
  • Best practices and implementation patterns
  • Troubleshooting guides
Connect once and get accurate, up-to-date Fish Audio knowledge in your coding environment.

​
Why Use MCP Integration?

Real-Time Docs

Access the latest API documentation without leaving your editor

Accurate Code

Generate working code based on current API specifications

Smart Assistance

Get context-aware help for debugging and optimization

​
Quick Setup

Add Fish Audio’s MCP server to your coding agent: 
{
  "servers": {
    "fish-audio-docs": {
      "url": "https://docs.fish.audio/mcp",
      "name": "Fish Audio Documentation"
    }
  }
}

​
Setup by Platform

1

Open Settings

Navigate to Claude Code settings configuration
2

Add MCP Server

Add the Fish Audio documentation server:
{
  "servers": {
    "fish-audio-docs": {
      "url": "https://docs.fish.audio/mcp",
      "name": "Fish Audio Documentation",
      "description": "Official Fish Audio API documentation"
    }
  }
}
3

Restart Claude Code

Restart the application to activate the MCP connection
4

Verify Connection

Ask Claude Code: “What Fish Audio models are available?”

​
Using the Integration

​
Example Queries

Once connected, ask your coding agent questions naturally:

Authentication

“How do I authenticate with Fish Audio API?”

TTS Example

“Show me Python code for text-to-speech”

Emotions

“What emotion parameters are available?”

WebSocket

“Help me implement real-time streaming”

​
Code Generation Examples

Ask: “Generate a Python function for text-to-speech with Fish Audio”
from fish_audio import FishAudioClient

def text_to_speech(text: str, voice_id: str, output_file: str):
    """Convert text to speech using Fish Audio API"""
    client = FishAudioClient(api_key="your-api-key")

    response = client.tts.create(
        text=text,
        model_id=voice_id,
        format="mp3"
    )

    with open(output_file, "wb") as f:
        f.write(response.audio_data)

    return output_file

​
Available Documentation

Your coding agent can access:

API Reference

Complete endpoint documentation with parameters

SDK Guides

Python SDK usage and examples

Best Practices

Optimization patterns and tips

Models & Pricing

Available models and rate limits

Voice Cloning

Custom voice creation guides

Troubleshooting

Common issues and solutions

​
Advanced Usage

​
Custom Commands

Create agent workflows for common tasks: 
"Create a complete voice generation pipeline with:
- Authentication
- Voice selection
- Emotion control
- Error handling
- Audio export"

​
Context-Aware Features

With MCP integration, your agent can:
  • Suggest appropriate models based on use case
  • Handle rate limiting automatically
  • Provide inline documentation
  • Validate API calls against specifications
  • Recommend optimization strategies

​
Troubleshooting

​
Security

Your data is safe:
  • MCP provides read-only access to public documentation
  • No API keys are transmitted through MCP
  • All connections use HTTPS encryption
  • No user queries or usage data is stored

​
Next Steps

API Introduction

Start with Fish Audio API basics

Python SDK

Install and configure the Python SDK

TTS Best Practices

Learn text-to-speech optimization

Voice Cloning Guide

Create custom voice models

​
Support

Need help with MCP integration?