Frame Realtime Gemini Voicevision
Realtime voice and vision on Brilliant Labs Frame.
- Est. cost
- Cost unknown
- Posted
- GitHub stars
- 82 (GitHub)
Overview
Brilliant Labs' official demo of a real-time multimodal assistant on Frame AR glasses, using Gemini's Multimodal Live API for voice and vision.
How it works
The phone app streams audio and camera images from Frame to Gemini and plays the reply. The UI shows the images sent to the model plus turn-taking and interruption data. The system prompt is editable, and you can choose from Gemini's Puck, Charon, Kore, Fenrir and Aoede voices. There's an Android APK; on iOS you build with Flutter and Xcode.
Hardware
- Brilliant Labs Frame
- phone
This page is a short summary written by HardwareLab. Build steps, code and photos belong to the creator; follow “View original” for the full project.
More in Smart Glasses
See all 31Hermes Glasses
Voice + vision assistant for Ray-Bans and Realtek-based glasses.
- Meta Ray-Ban
- AiSee/Realtek glasses
AdvancedCost unknown22Visionbridge AI Glasses
ESP32 glasses firmware with voice, camera, display and MCP.
- ESP32
- camera
- display
- +1 more
AdvancedCost unknown5Visionclaw
Modular glasses: stock frame plus 3D-printed AI temples.
- XIAO ESP32-S3
- bone-conduction audio
- 3D-printed temples
IntermediateCost unknown2