Install the skill
.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
/.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
The Fish Audio MCP server athttps://api.fish.audio/mcp gives your agent tools instead of docs: it can search the voice library, generate speech, and transcribe audio with your Fish Audio account (OAuth sign-in, no API key). See the MCP server guide for client setup and the tool list.
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: support@fish.audio
- Issues: GitHub
- Community: Discord

