- Auto-Record your voice
- Convert it to the text
- Ask to GPT-3.5 (ChatGPT Turbo model)
Not working on WSL (pyaudio cannot access to your microphone)
- Set your GCP speech-to-text-v2 and get your proper GCP service user
- Get your OpenAI API key
- Check portaudio
- Windows : Do nothing
- macOS : brew install portaudio
- Linux : sudo apt-get install python3-pyaudio
- Install all requirements.txt
- Modify 'config.py' as you wish
- Write your environment variables to '.env' (gitignored)
- execute main.py