---
title: MOSS-Speech Demo
sdk: gradio
sdk_version: 5.47.2
app_file: app.py
python_version: '3.12'
pinned: true
short_description: True Speech-to-Speech Language Model
---
# MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance
ι
θ―»[δΈζ](./README_ZH.md)ηζ¬.
---
## π Introduction
Spoken dialogue systems often rely on cascaded pipelines that transcribe, process, and resynthesize speech, which limits expressivity and discards paralinguistic cues. **MOSS-Speech** directly understands and generates speech without relying on text intermediates, enabling end-to-end speech interaction while preserving tone, prosody, and emotion.
Our approach combines a **modality-based layer-splitting architecture** with a **frozen pre-training strategy**, leveraging pretrained text LLMs while extending native speech capabilities. Experiments show state-of-the-art results in spoken question answering and competitive speech-to-speech performance compared to text-guided systems.
Welcome to check out the system's [demonstration video](https://moss-speech.open-moss.com/).
---
## π Key Features
- **True Speech-to-Speech Modeling**: No text guidance required.
- **Layer-Splitting Architecture**: Integrates modality-specific layers on top of pretrained text LLM backbones.
- **Frozen Pre-Training Strategy**: Preserves LLM reasoning while enhancing speech understanding and generation.
- **State-of-the-Art Performance**: Excels in spoken question answering and speech-to-speech tasks.
- **Expressive & Efficient**: Maintains paralinguistic cues often lost in cascaded pipelines, such as tone, emotion, and prosody.
---
## π Repository Contents
- `gradio_demo.py` β Gradio-based web demo script for quickly experiencing speech-to-speech functionality.
- `generation.py` β Core generation script for producing output speech from input speech, suitable for inference and batch processing.
---
## π οΈ Installation
```bash
# Clone the repository
git clone https://github.com/OpenMOSS/MOSS-Speech
cd MOSS-Speech
# Install dependencies
pip install -r requirements.txt
```
---
## π Usage
Launch the web demo
```sh
python3 gradio_demo.py
```
---
## License
- The code in this repository is released under the [Apache 2.0](LICENSE) license.
---
## Acknowledgements
- [Qwen](https://github.com/QwenLM/Qwen3): We use Qwen3-8B-Instruct as the base model.
- We thank an anonymous colleague for Character Voice!
---
## π Citation
If you use this repository or model in your research, please cite:
```bibtex
@article{moss_speech2025,
title={MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance},
author={SLM Team},
institution={Shanghai Innovation Institute, Fudan University, MOSI},
year={2025},
note={Official implementation available at https://huggingface.co/fnlp/MOSS-Speech}
}
or
@misc{moss_speech2025,
author = {SLM Team},
title = {MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance},
year = {2025},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/OpenMOSS/MOSS-Speech}},
}
```
