Today we launch Fish Audio S2, a new generation of expressive TTS with absurdly controllable emotion.

- open-source
- sub 150ms latency
- multi-speaker in one pass

Real freedom of speech starts now 👇 Fish S2 is fully open-sourced.
Shout-out to SGLang for powering the stack.

GitHub: github.com/fishaudio/fish… HuggingFace: huggingface.co/fishaudio/s2-p…

What would you build with it?

Introducing Fish Speech 1.5 🎉 - Making state-of-the-art TTS accessible to everyone!

Highlights:
- #2 ranked on TTS-Arena (as "Anonymous Sparkle")
- 1M hours of multilingual training data
- 13 languages supported, including English, Chinese, Japanese & more
- <150ms latency with high-quality instant voice cloning
- Pretrained model now open source
- Cost-effective self-hosting or cloud options

Let's check out the details 🧵⬇️ Try Fish Speech 1.5:
🎮 Playground: fish.audio
💻 Code: github.com/fishaudio/fish…
🎯 Demo: huggingface.co/spaces/fishaud…
🏆 See our rank: huggingface.co/spaces/TTS-AGI…
Let's revolutionize voice tech together! 🐠