S2.1 Pro

#3 in Text-to-Speech (TTS)

Fish Audio · pro · 3× · last seen Jul 30, 2026

74

Momentum

S2.1 Pro is Fish Audio's current flagship Text-to-Speech model, building on the open-weight S2-Pro model and available via the Fish Audio API as both a paid production version and a free developer version (s2.1-pro-free). The model supports 83 languages, Voice-Cloning from seconds of reference audio, real-time streaming with low latency, and word-level control of emotion and speaking style via natural text markers (tags). It officially launches publicly on July 28, 2026 as part of a funding round, following its announcement as a free API in June 2026.

Sources (3)