fish-audio-api
Fish Audio public API
Use this skill when a video needs Fish narration. The release uses the official POST https://api.fish.audio/v1/tts endpoint. It does not ship a web-session proxy, cookies, an account, or a voice. Node.js 22.20 or later is required. Install FFmpeg/ffprobe for the video audio pipeline.
Configure locally
Copy env.example to the video project's .env, ensure .env is ignored by Git, then fill it locally. Never request that users paste credentials into chat. Existing process environment values take precedence over .env. Scripts never print secret values or upstream error bodies.
| Variable | Meaning |
|---|---|
FISH_API_KEY |
API key created in the user's Fish account; required for generation. |
FISH_REFERENCE_ID |
A voice ID the user has permission to use; required unless a project explicitly supplies one. |
FISH_MODEL |
Defaults to s2.1-pro-free; supported choices also include s1, s2-pro, s2.1-pro. Account access and quotas are provider-controlled. |
No silent model fallback is allowed. An unknown model fails locally, because the provider may otherwise choose a paid default. Availability and pricing can change; check the account before generation. Setting a key does not itself authorize a charge: run synthesis only for the user's requested scope.
Generate and revise
For a scaffolded HyperFrames project, edit scripts/narration.json. Its voice.referenceId and voice.model may be null to use the environment. All other voice settings are explicit in the template. Preview one short paragraph before producing a whole narration.