Artificial IntelligenceReleasedUpdated Jul 1, 2026

AiVi — See & Speak

Camera-based AI tools rarely feel like a real conversation about what's in front of you.

Why this matters

Independence often depends on quickly understanding a space, an object, or a document. A visual interpreter that talks with you — not at you — puts the person back in charge of the interaction.

Current idea
An AI visual interpreter that discusses what your camera sees in real time. Point your camera at anything and have a live, voice-driven conversation about it, with customizable AI agents, spatial audio voice commands, and task-specific focus modes. Also available as a downloadable Mac app.
Accessibility notes
Voice-first interaction, customizable agents, spatial audio cues, keyboard-accessible controls, and screen-reader friendly labeling throughout.
What was learned
People stay engaged much longer when the assistant can be interrupted, redirected, and refocused mid-conversation.

Development updates

Progress in public

  1. Live web app and downloadable Mac app both available.

  2. Spatial audio voice commands and focus modes shipped.

Feedback

Have thoughts on this project?

Head to the Ideas board to share a related barrier or idea. Attribution is optional.

Open the Ideas board