---
license: cc-by-nc-4.0
language:
- en
- zh
pipeline_tag: text-to-speech
tags:
- text-to-speech
- zero-shot-tts
- waveform-generation
datasets:
- amphion/Emilia-Dataset
---

# WavTTS

This repository hosts the official WavTTS checkpoint for zero-shot text-to-speech generation at 16 kHz. Please refer to the [GitHub repository](https://github.com/cwx-worst-one/WavTTS) and [paper](https://arxiv.org/abs/2606.03455) for more details.

## Files

- `model_1200000.pt`: official WavTTS checkpoint.
- `vocab.txt`: matching vocabulary file for the released checkpoint.

## Usage

Please use this checkpoint with the WavTTS codebase:

```bash
git clone https://github.com/cwx-worst-one/WavTTS
cd WavTTS
pip install -e .
```

Run inference with the default checkpoint:

```bash
wavtts_infer-cli \
  --model WavTTS \
  --ref_audio "path/to/reference.wav" \
  --ref_text "The transcription of the reference audio." \
  --gen_text "The text you want to synthesize."
```

The default WavTTS configuration downloads `model_1200000.pt` from this repository automatically. To use the files explicitly, set:

```toml
ckpt_file = "hf://worstchan/WavTTS/model_1200000.pt"
vocab_file = "infer/examples/vocab.txt"
```

## License

The released model weights are licensed under CC BY-NC 4.0 due to the license restrictions of the Emilia training dataset. The WavTTS codebase is released under the MIT License.

## Citation

If you find WavTTS useful, please cite the paper:

```bibtex
@article{chen2026wavtts,
  title={WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modeling},
  author={TODO},
  journal={TODO},
  year={2026}
}
```