Update app.py

app.py

@@ -65,6 +65,7 @@ def run(history, text, image, audio_upload, audio_mic):
     
 with gr.Blocks() as demo:
     gr.Markdown("## 🤖 Multi-modal LLM")
+    gr.Markdown("This is a multi-modal LLM that takes text, image and audio as inputs.")
 
     with gr.Row():
         with gr.Column(scale=4):