---
title: FishAudio S2 Pro TTS
emoji: 🐟
colorFrom: indigo
colorTo: purple
sdk: gradio
app_file: app.py
pinned: false
short_description: Text to speech with fishaudio/s2-pro
models:
  - fishaudio/s2-pro
---

# FishAudio S2 Pro TTS

This Space is a simple text-to-speech app built around `fishaudio/s2-pro`.

## Notes

- It uses `trust_remote_code=True` to load the upstream model.
- It is stateless, so repeated inputs should not hit chat-history bugs.
- If the upstream repo needs a custom runtime beyond standard Transformers, you may need a Docker Space or stronger hardware.
- You mentioned this clone command:

```bash
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/fishaudio/s2-pro
```

That command skips large LFS files during clone. This Space instead loads the model from the Hub at runtime.