Update app.py

app.py

@@ -68,6 +68,10 @@ def text2speech(text):
 define voice -> gpt -> text -> voice workflow
 """
 def transcribe(audio):
+    messages = chat.generate_dialogue(audio)
+    voice_path = chat.synthesize_voice(messages)
+    chat_text = "\n".join([f"{msg['role']}: {msg['content']}" for msg in messages])
+    return voice_path, chat_text
     #global messages
 
     """
@@ -124,11 +128,12 @@ def transcribe(audio):
 
 output_text = gr.outputs.Textbox(label="Chat Messages")
 
-output_audio = gr.outputs.Audio(type = "filepath", label="AI Assistant")
-
-gr.Interface(fn=transcribe, \
-            inputs=gr.Audio(source="microphone", type="filepath",label="Speak here..."), \
-            outputs=[output_audio, output_text], \
-            live=True,\
-            allow_flagging='never')\
-            .launch()
+output_audio = gr.outputs.Audio(label="Synthesized Voice")
+output_text = gr.outputs.Textbox(label="Chat Messages")
+gr.Interface(
+    fn=transcribe, 
+    inputs=gr.inputs.Audio(source="microphone", label="Speak here..."), 
+    outputs=[output_audio, output_text], 
+    live=True,
+    allow_flagging='never'
+).launch()