Out of Scope (Future Work)
- Video description (requires video frame extraction, much more
complex)
- Audio transcription
- Document OCR / summary
- Image sending from AQUAPING (the client currently has no image
picker)
- Inline image thumbnail rendering (screen is too small)
- Tap-to-view full image on phone (requires deep-linking to
iMessage)
- Real-time image streaming (Live Photos, screen sharing)
- Custom vision models (e.g., fine-tuned for game screenshots)