| title: Audio Interaction Model | |
| emoji: 🎙️ | |
| colorFrom: blue | |
| colorTo: red | |
| sdk: gradio | |
| sdk_version: 6.15.1 | |
| app_file: app.py | |
| short_description: Streaming audio-language model that listens and responds | |
| python_version: "3.12" | |
| startup_duration_timeout: 1h | |
| Audio Interaction Model demo — a streaming audio-language model that perceives audio | |
| and decides when to speak. Upload or record audio and get a text response. | |
| Model: [zhifeixie/AudioInteraction](https://huggingface.co/zhifeixie/AudioInteraction) | |
| Paper: [arXiv:2606.05121](https://arxiv.org/abs/2606.05121) | |
| Code: [GitHub](https://github.com/xzf-thu/Audio-Interaction) |