fishaudio / text-to-speech updated 4 months ago

s2-pro

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 release includes model weights, fine-tuning code, and an SGLang-based streaming inference engine.

Params
4.6 B
Context
Downloads 30d
368 K
Likes
1,196
Licence: other Not gated SAFETENSORS 83 languages View on Hugging Face ↗

Download history

tracking started — chart appears after 7 days of snapshots (1 recorded)
368 K downloads in the last 30 days

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors bf16 9.1 GB 11.2 GB ✅ Runs comfortably
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Parameters
4.6 B
Tensor type
BF16
Licence
other
First seen on the Hub
2026-03-09
Training datasets
undisclosed
Added to our catalog
2026-08-06