Update app.py

app.py

@@ -107,7 +107,7 @@ def greet(product,description):
             else:
                 text_str = a_list[0]
             samples = tts.synthesize(text_str, speakers[-1])
-        yield gr.Audio(value=(tts.get_sampling_rate(), samples))
+        yield gr.Audio(value=(tts.get_sampling_rate(), samples)), text_str
     else:
         output = llm.create_chat_completion(
         messages=[
@@ -129,8 +129,9 @@ def greet(product,description):
                     tts = TTS(os.path.join(os.getcwd(), tts_model_str))
                     speakers = tts.get_speakers()
                     samples = tts.synthesize(delta.get('content', ''), speakers[-1])
-        yield gr.Audio(value=(tts.get_sampling_rate(), samples))
+                    partial_message = partial_message + delta.get('content', '')
+                yield gr.Audio(value=(tts.get_sampling_rate(), samples)), partial_message
 
 audio = gr.Audio()
-demo = gr.Interface(fn=greet, inputs=["text","text"], concurrency_limit=10, outputs=audio)
+demo = gr.Interface(fn=greet, inputs=["text","text"], concurrency_limit=10, outputs=[audio,"text"])
 demo.launch()