Available Models
Currently available models:- Fish Audio S2 (Recommended:
s2.1-pro) - Latest generation with best performance - Transcribe 1 Pro (
transcribe-1-pro) - Speech to text
Deprecated Models
- s1 - S1 is deprecated and will be retired on December 31, 2026. After that date, requests that specify
s1are served bys2.1-pro. See Migrate from S1. - transcribe-1 - transcribe-1 is deprecated and will be retired on December 31, 2026. After that date, the requests it serves, including those with no
modelheader and those through the compatible endpoints, are served bytranscribe-1-pro. See Migrate from transcribe-1. - speech-1.6 - Fish Speech v1.6 has been deprecated on February, 28th, 2026
- speech-1.5 - Fish Speech v1.5 has been deprecated on February, 28th, 2026
We recommend using
s2.1-pro for all new projects. If you use s1,
follow Migrate from S1
before December 31, 2026. If your speech-to-text requests are served by
transcribe-1, follow
Migrate from transcribe-1
before the same date.Support
Need help? Check out these resources:- API Reference - Complete API documentation
- Create a Voice Clone - Create a voice clone model
- Generate Speech - Generate realistic speech
- Real-time Streaming - WebSocket for real-time streaming
- Discord Community - Get help from the community
- Support Email - Contact our support team