Update app.py

app.py

@@ -37,7 +37,7 @@ def infer(image_input, manual_caption, duration_in, seed, caption_output):
     sound = audio_gen(cap, duration_in, 2.5, seed, 3, fn_index=0)
     
     #return cap, sound[1], gr.Textbox.update(placeholder=f"{ph_update}{ph_message}"), gr.Group.update(visible=True)
-    return cap, sound[1], gr.Group.update(visible=True)
+    return cap, sound, gr.Group.update(visible=True)
 
 title = """
     <div style="text-align: center; max-width: 700px; margin: 0 auto;">