Update app.py

app.py

@@ -75,7 +75,7 @@ with gr.Blocks(css="style.css") as demo:
         gr.HTML(title)
     
         input_img = gr.Image(type="filepath", elem_id="input-img")
-        manual_cap = gr.Textbox(label="Image description (optional)")
+        manual_cap = gr.Textbox(label="Manual Image description (optional)", placeholder="If you're not happy with sound result, you can manually describe the scene depicted in your image :)")
         caption_output = gr.Textbox(label="Caption", lines=1, visible=False, elem_id="text-caption")
         sound_output = gr.Audio(label="Result", elem_id="sound-output")