Update app.py

app.py

@@ -12,4 +12,13 @@ iface = gr.Interface(launch,
                      inputs=gr.Image(type='pil'),
                      outputs="text")
 
-iface.launch()
+tts_pipe = pipeline("text-to-speech",
+                    model="kakao-enterprise/vits-ljs")
+text = iface.launch()
+
+narrated_text = tts_pipe(text)
+
+from IPython.display import Audio as IPythonAudio
+
+IPythonAudio(narrated_text["audio"][0],
+             rate=narrated_text["sampling_rate"])