Providers
Fish Audio
Open-source Fish Audio S2 text-to-speech through the Speechbase gateway, with audio tags and voice cloning.
| Prefix | fish-audio |
| Default model | s2-pro |
| Provider key | Connect under Provider Keys |
Route to Fish Audio by prefixing the model with fish-audio/. s2-pro is an
open-source model with streaming, audio tags, and voice cloning.
Models
| Model | Streaming | Audio tags | Voice cloning | Open source | Languages |
|---|---|---|---|---|---|
s2-pro | Yes | Yes | Yes | Yes | 10 |
Usage
curl -X POST https://api.speechbase.ai/v1/audio/speech \
-H "Authorization: Bearer $SPEECHBASE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"mode": "inline",
"model": "fish-audio/s2-pro",
"voice": "default",
"text": "Hello from Speechbase!",
"output": "mp3"
}' --output hello.mp3Replace voice with a Fish Audio reference (model) ID, or register a cloned
voice as a saved Voice and address it by
voiceId.
Voice cloning
s2-pro supports cloning from a reference sample. Clone into a saved
Voice, then use mode: "voice" — inline
requests take a plain voice string only.
Provider options
Anything in providerOptions is forwarded to the Fish Audio API unchanged.