Update app.py

app.py

@@ -23,7 +23,7 @@ def get_pipeline_prediction(pil_image):
     
     processed_image = render_results_in_image(pil_image,
                                             pipeline_output)
-    return [processed_image, narrated_text]
+    return [processed_image, narrated_text["audio"]]
 
 demo = gr.Interface(
   fn=get_pipeline_prediction,