Update app.py

app.py

@@ -93,7 +93,7 @@ with gr.Blocks(title="Whisper, Vicuna, & TTS Demo") as demo:  # Updated title
     with gr.Tab("Transcribe & Synthesize"):
         mic_input = gr.Audio(sources="microphone", type="filepath", label="Speak Here")
         transcription_output = gr.Textbox(lines=5, label="Transcription and Vicuna Response")
-        audio_output = gr.Audio(label="Synthesized Speech", type="numpy") # Important: type="numpy"
+        audio_output = gr.Audio(label="Synthesized Speech", type="numpy", autoplay=True)
         transcription_state = gr.State(value="")
         mic_input.change(
             fn=process_audio,  # Call the combined function