Fish Audio S2 Pro v1.0
Fish Audio S2 Pro is an advanced text-to-speech (TTS) model developed by Fish Audio, offering fine-grained inline control over prosody and emotion. Trained on over 10 million hours of audio data across more than 80 languages, it combines reinforcement learning alignment with a dual-autoregressive architecture to deliver high-quality, expressive speech synthesis.
Fine-grained inline control over prosody and emotion
Supports over 80 languages
Dual-autoregressive architecture for efficient inference