Fish Audio launches S2.1 Pro with support for 83 languages

Fish Audio launched S2.1 Pro as its recommended production voice model and made it available through the Fish Audio API.

The model highlights fast time-to-first-audio, support for 83 languages, multi-speaker dialogue, and bracket-tag voice direction.

It also supports short-sample voice cloning and integration with agent workflows, with a free tier for development and testing.

The release is aimed at real-time voice agents and other low-latency speech apps that need natural conversational control.