AI Coding Agents

Install the Fish Audio skill so your coding agent writes correct SDK and API code

Install the Fish Audio agent skill, and your coding agent — Claude Code, Cursor, Codex, and others — writes correct, current Fish Audio code: right method names, units, and error types, instead of guessing.

Install the skill

npx skills add https://docs.fish.audio

This installs both Fish Audio skills into your agent (a canonical copy in .agents/skills/, with symlinks for Claude Code and Cursor). Run npx skills update later to refresh them.

fish-audio-sdk

Python (fish-audio-sdk) and JavaScript (fish-audio) — exact method signatures and defaults, sync + async, model selection, and the real exception types.

fish-audio-api

Raw REST + WebSocket for any language or edge runtime — auth, endpoints, MessagePack/JSON/multipart rules, and the streaming protocol.

Install options

All skills

npx skills add https://docs.fish.audio

Want to read them before installing? The skills are served at /.well-known/agent-skills/index.json, with each skill’s markdown at /.well-known/agent-skills/<name>/SKILL.md.

Try it

Once installed, ask your agent in plain language — it will use the correct client, methods, and error types:

TTS in a cloned voice

“Generate speech with Fish Audio in a cloned voice and save it to a file.”

Transcribe with timestamps

“Transcribe speech.wav with Fish Audio and print the segments.”

Stream from an LLM

“Stream an LLM’s tokens to Fish Audio TTS over the WebSocket.”

Raw API, any language

“Call the Fish Audio TTS REST API from Go, no SDK.”

Or connect via MCP

Prefer live documentation search inside your editor over a self-contained skill file? Connect the Fish Audio MCP server, which serves the latest docs to your agent.

Claude Code

claude mcp add --transport http fish-audio --scope project https://docs.fish.audio/mcp

This writes a .mcp.json in your project root. Verify with claude mcp list (you should see fish-audio), then ask “What Fish Audio TTS models are available?”

Installation scopes

• --scope project (recommended): config in .mcp.json, version-controlled and shared with your team.
• --scope user: global across your projects, private to your account.
• --scope local (default): project-specific and private to you.

Cursor

Open the command palette (Cmd/Ctrl+Shift+P) → “Open MCP settings” → “Add custom MCP”, and add:

{
  "mcpServers": {
    "fish-audio": { "url": "https://docs.fish.audio/mcp" }
  }
}

Save and reload Cursor, then ask “What Fish Audio TTS models are available?”

Windsurf

Go to Settings → Cascade → MCP Servers → View raw config (~/.codeium/windsurf/mcp_config.json) and add:

{
  "mcpServers": {
    "fish-audio": { "url": "https://docs.fish.audio/mcp" }
  }
}

Save, refresh, then in Cascade ask “Search Fish Audio docs for TTS API usage.”

Skill vs MCP: the skill is a self-contained instruction file that works offline after install; MCP fetches the latest docs live. You can use both. This site also exposes llms.txt and llms-full.txt for agents that fetch docs directly.

Next steps

Get your API key

Create a key and make your first request.

Text to Speech

Voices, formats, streaming, and the direct API.

API reference

Endpoints, parameters, and the OpenAPI schema.

Errors

Status codes, retries, and SDK exception handling.

Support

• Technical support: [e-mail]
• Issues: GitHub
• Community: Discord