hugpadhugpad

fishaudio / s2-pro

Audio4.6B48.3K1.5KUpdated Mar 11, 2026
Hugging Face

Downloads

48.3K

Likes

1.5K

Last updated

Mar 11, 2026

License

fish-audio-research-license

Fish Audio S2 Pro is a leading text-to-speech (TTS) model with fine-grained inline control of prosody and emotion. Trained on over 10M+ hours of audio data across 80+ languages, the system combines reinforcement learning alignment with a dual-autoregressive architecture. The r…

Tasks & library

  • text to speech

Tags

  • fish_qwen3_omni
  • text-to-speech
  • instruction-following
  • multilingual
  • zh
  • en

Technical specifications

Parameters4.6B
LibraryNot available
Languages83 languages
Licensefish-audio-research-license