Update app.py

app.py

@@ -10,14 +10,13 @@ tts_pipe = pipeline("text-to-speech",
 
 def launch(input):
     out = pipe(input)
-    narrated_text = tts_pipe(out[0]['generated_text'])
-    IPythonAudio(narrated_text["audio"][0],
-             rate=narrated_text["sampling_rate"])
-    return out[0]['generated_text']
+    out_tts = tts_pipe(out[0]['generated_text'])
+    return out[0]['generated_text'], (out_tts["sampling_rate"],out_tts["audio"][0])
+
 
 iface = gr.Interface(launch,
                      inputs=gr.Image(type='pil'),
-                     outputs="text")
+                     outputs=["text","audio"])
 iface.launch()