showing text in chatbot input and audio in output

app.py

@@ -29,7 +29,6 @@ def run_model(text):
 def get_output(history, audio):
 
     txt = p(audio)["text"]
-    history.append(( (audio, ) , txt))
     audio_path = 'response.wav'
     response = run_model(txt)
     # Remove all text from SOURCES: to the end of the string
@@ -39,7 +38,7 @@ def get_output(history, audio):
     # split audio by / and keep the last element
     # audio = audio.split("/")[-1]
     # audio = audio + ".wav"
-    history.append(( (audio, ) , (audio_path, )))
+    history.append(( txt , (audio_path, )))
     print(history)
     return history
 
@@ -58,7 +57,7 @@ with gr.Blocks() as demo:
             ).style(container=False)
 
         with gr.Column(scale=0.15):
-            audio = gr.Audio(source="microphone", type="filepath").style(container=False)
+            audio = gr.Audio(source="microphone", type="filepath", suffix=".wav").style(container=False)
 
     txt.submit(add_text, [chatbot, txt], [chatbot, txt], postprocess=False).then(
         bot, chatbot, chatbot