Changing The Voice (and improving quality)

[WearilessSpy603]

Changing the Voice in Your Script

If you want to change the voice in your script, you can do it easily by modifying the main.py file. Follow these steps:

1. Open the main.py file and scroll down until you find the following code:

   def speak(text):
       print("[Miles is generating speech...]")
       if not text:
           print("No text provided to speak.")
           return

       try:
           response = client.audio.speech.create(
               model="tts-1-hd",
               voice="shimmer",
               input=text
           )

           byte_stream = io.BytesIO(response.content)

           audio = AudioSegment.from_file(byte_stream, format="mp3")
           audio.export("output.mp3", format="mp3")

           print("[Miles is speaking a response...]")
           play(audio)

       except Exception as e:
           print(f"An error occurred: {e}")

           openai.api_key = api_key
   client = OpenAI(api_key=api_key)

   def speak_no_text(text):
       if not text:
           print("No text provided to speak.")
           return

       def _speak():
           try:
               response = client.audio.speech.create(
                   model="tts-1-hd",
                   voice="shimmer",
                   input=text
               )

2. Edit the voice parameter:
   Change the name after voice= to one of the other OpenAI voices found here. The available voices are Alloy, Echo, Fable, Onyx, Nova, and Shimmer.

3. Improve Audio Quality:
   To get better audio quality, change tts-1 to tts-1-hd. Note that this will increase latency slightly.

Hope this helps a few people out!