MMLForge Search models, datasets, tasks… Start free
Home › Models › Text To Speech › fishaudio/s2-pro
S

fishaudio/s2-pro

Text To Speech·fishaudio· 434.2K· 1.1K
other Text To Speech 4.6B params

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.

Open in MLForge Sign up free Desktop app Source ↗
# pull & run locally
pip install mlforge-sdk && mlforge pull fishaudio/s2-pro

Model details

Task
Text To Speech
Provider
fishaudio
Parameters
4.6B
Size
10 GB
License
other
Downloads
434.2K
Likes
1.1K
Paper
arXiv:2603.08823
Updated
2026-03-11

About fishaudio/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.

Related Text To Speech

K hexgrad/Kokoro-82M Text To Speech 15.5M 6.4K 🤗 HF X coqui/XTTS-v2 Text To Speech 9.2M 3.6K 🤗 HF C ResembleAI/chatterbox Text To Speech 2.2M 1.7K 🤗 HF Q Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice Text To Speech ·1.9B params 2.0M 1.6K 🤗 HF Q Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice Text To Speech ·905.8M params 1.2M 163 🤗 HF O k2-fsa/OmniVoice Text To Speech ·612.6M params 1.0M 1.1K 🤗 HF

Browse all Text To Speech models →