Added st.session_state.messages.append(audio_convert)

app.py

@@ -105,6 +105,8 @@ def launch_bot():
         if st.session_state.messages[-1]["role"] == "assistant" or st.session_state_messafes[-1]["role"] == "content":
             audio_result = st.button("Convert to Audio 🔊") 
             if audio_result:
+                with st.chat_message("text-to-speech"):
+                with st.spinner("Thinking..."):
             #text-to-speech
                 print("Calling in Text-to-speech via suno/bark-small")
                 synthesiser = pipeline("text-to-speech", "suno/bark-small")
@@ -117,8 +119,9 @@ def launch_bot():
                 audio_file = open('bark_out.wav', 'rb')
                 audio_bytes = audio_file.read()
     
-                st.audio(audio_bytes, format='audio/wav')
-    
+                audio_convert = st.audio(audio_bytes, format='audio/wav')
+                st.session_state.messages.append(audio_convert)
+                
                 sample_rate = 44100  # 44100 samples per second
                 seconds = 2  # Note duration of 2 seconds
                 frequency_la = 440  # Our played note will be 440 Hz