How Aura Works

The flow is simple:

1. Aura's microphone captures audio continuously

2. The camera captures images at set intervals

3. Both are sent to the backend over Wi-Fi

4. The backend transcribes audio via Deepgram or Whisper

5. Images are understood via GPT-4o Vision or Moondream

6. Everything is summarized and stored

7. You see it all in the Omi app on your phone

The ESP32-S3 handles capture and transmission. The backend handles all AI processing. Your phone is just the interface.