update！！！

app.py

@@ -212,8 +212,9 @@ variant = gr.Dropdown(label="Model Variant", choices=list(all_model_cfg.keys()),
 # """
 
 description_text = """
-**MeanAudio** is a novel text-to-audio generator that uses **MeanFlow** to synthesize realistic and faithful audio in few sampling steps. It achieves state-of-the-art performance in single-step audio generation and delivers strong performance in multi-step audio generation.
-[📖 **Arxiv**](https://arxiv.org/abs/2508.06098) | [🤗 **Model**](https://huggingface.co/AndreasXi/MeanAudio) | [🚀 **Space**](https://huggingface.co/spaces/chenxie95/MeanAudio) | [🌐 **Project Page**](https://meanaudio.github.io/) | [💻 **GitHub**](https://github.com/xiquan-li/MeanAudio)
+### **MeanAudio** is a novel text-to-audio generator that uses **MeanFlow** to synthesize realistic and faithful audio in few sampling steps. It achieves state-of-the-art performance in single-step audio generation and delivers strong performance in multi-step audio generation.
+
+### [📖 **Arxiv**](https://arxiv.org/abs/2508.06098) | [💻 **GitHub**](https://github.com/xiquan-li/MeanAudio) | [🤗 **Model**](https://huggingface.co/AndreasXi/MeanAudio) | [🚀 **Space**](https://huggingface.co/spaces/chenxie95/MeanAudio) | [🌐 **Project Page**](https://meanaudio.github.io/)
 """
 gr_interface = gr.Interface(
     fn=generate_audio_gradio,