Faster Speech To Speech:

[]

A super fast and quick way to implement a speech to speech model using:

If you wish to just call Google TTS API just run

python s2s.py --gtts

1. Ensure you install the requirements via

   pip install requirements.txt

2. Remember to sign up for Groq Playground and create an API_KEY

3. Run the script

   python s2s.py

Just run python s2s.py followed by the following args commands you can try:

--output file_to_path : To set path for audio

--gtts: Enables Google TTS Service, else fallsback to Coqui TTS

--temperature (insert int): controls creativity of the model

--audio (audio_name): Sets name of your microphone

--model (model_name): Set model name (Default is llama3-70b-8192)