Skip to main content
Audio modelActive

Fish Audio S2.1 Pro

Fish Audio

Released
June 23, 2026
Data date
October 3, 2026
Model class
Languages

Fish Audio S2.1 Pro is the API endpoint for the newer S2.1 generation. It produces multilingual speech, supports voice cloning, and responds in about 90 milliseconds to first audio.

The free identifier s2.1-pro-free is announced through November 30, 2026 under fair-use rules and without an SLA. The offer’s terms govern data retention and commercial use. No separate S2.1 weights checkpoint is published.

Specifications and access

SpecificationValue and source
Model class
Speech synthesisSource
Access
Fish Audio APISource
Input
Text with voice and emotion controlSource
Output
Multilingual speechSource
API model ID
s2.1-pro-freeSource
Languages
83 languagesSource
Latency
About 90 milliseconds to first audioSource
Usage conditions
No SLA or guaranteed latency; possible retention and commercial-use restrictions applySource