added description for both interfaces

app.py

@@ -166,6 +166,7 @@ with gr.Blocks() as demo:
         inputs=tts_demo_inputs,
         outputs=tts_demo_output,
         title="Amphion Text-to-Speech",
+        description="[![Open in OpenXLab](https://cdn-static.openxlab.org.cn/app-center/openxlab_app.svg)](https://openxlab.org.cn/usercenter/Amphion) This demo offers an Amphion TTS pretrained model (VITS) for you to explore."
     )
     
     gr.Interface(
@@ -173,6 +174,7 @@ with gr.Blocks() as demo:
         inputs=tc_demo_inputs,
         outputs=tc_demo_outputs,
         title="Timbre Confusion",
+        description="In this section, you can choose two speakers to create a voice mix. Adjust the ‘confusion degree’ slider to achieve your desired mix ratio between the two speakers."
     )
 
     demo.queue()