Switched to gTTs for text-to-speech

app.py

@@ -10,6 +10,10 @@ import tempfile
 import streamlit as st
 from PIL import Image
 
+from gtts import gTTS 
+from io import BytesIO
+
+
 master_prompt = """
 As a Natural Farming Fertilizers Assistant, you will assist the user with any farming related question, always willing to answer any question and provide useful organic farming advice in the following format.
 ' ' '
@@ -110,49 +114,11 @@ def launch_bot():
         audio_result = st.button("Convert to Audio 🔊") 
         if audio_result:
             # with st.chat_message("assistant"):
-            st.write("Converting text to speech. This may take a few minutes.")
-                
-            #text-to-speech
-            print("Calling in Text-to-speech via suno/bark-small")
-                        
-            synthesiser = pipeline("text-to-speech", "suno/bark-small")
-                
-            speech = synthesiser(response, forward_params={"do_sample": True})
-    
-            # write to temp file: the scipy wav write bark_out.wav
-            fp.write(scipy.io.wavfile.write("bark_out.wav", rate=speech["sampling_rate"], data=speech["audio"]))
-
-            with st.chat_message("assistant"):
-                with st.spinner("Thinking..."):
-            # ST interface for audio
-                    print("Now we try to display the audio file in the app")
-                
-                # Temp file access
-                    fp.seek(0)
-                    audio_file = fp.read('bark_out.wav', 'rb')
-                    
-                    audio_bytes = audio_file.read()
-
-                # Close and delete temp file
-                    fp.close()
-                    
-            st.session_state.messages.append({"role": "assistant", "content": 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
-                    
-                # Generate array with seconds*sample_rate steps, ranging between 0 and seconds
-                #t = np.linspace(0, seconds, seconds * sample_rate, False)
-                    
-                # Generate a 440 Hz sine wave
-                #note_la = np.sin(frequency_la * t * 2 * np.pi)
-                #st.audio(note_la, sample_rate=sample_rate)
-
-
-
+            st.write("Converting text to speech. This may take a few minutes.")            
+            sound_file = BytesIO()
+            tts = gTTS('Add text-to-speech to your app', lang='en')
+            tts.write_to_fp(sound_file)
+            st.audio(sound_file)
                 
 if __name__ == "__main__":
     launch_bot()