Update app.py

app.py

@@ -9,7 +9,7 @@ def multimodal_qa_app(image: Image.Image, audio_path: str):
     question_text = transcribe_audio(audio_path)
     answer = get_image_answer(image, question_text)
     audio_response = text_to_speech(answer)
-    return answer, audio_response
+    return question_text, answer, audio_response
 
 interface = gr.Interface(
     fn=multimodal_qa_app,
@@ -18,6 +18,7 @@ interface = gr.Interface(
         gr.Audio(type="filepath", label="Ask a Question via Mic (10s max)")
     ],
     outputs=[
+        gr.Textbox(label="Transcribed Question"),
         gr.Textbox(label="Answer"),
         gr.Audio(label="Spoken Answer")
     ],