python -m venv .venv
.venv/Scripts/activate
pip install -r requirements.txt
python main.py
- Keep a transcript of all the things the user has heard (filter out the garbage)
- Try using an open source TTS (or stick to elevenlabs).
- Use voice converter? or is it too heavy in resources? I want Lilas Ikuta for Japanese and Kafka for english.
- Plan out the hardware required to support teh software (this focuses on being lightweight, this is not AI, it is solely API)
- Implement a deafen feature that only activates when you flick a switch or press a button
- Find a translator API