Voice vs SightSense AI

This innovative app offers audio feedback on the user’s foundation, eyeshadow and lipstick application, creating a more accessible beauty experience for the Blind and visually impaired. How It Works: The AI-powered Voice-enabled Makeup Assistant leverages machine learning and voice instruction technologies to learn your preferences and provide audio feedback when you ask. After you apply your foundation, eyeshadow or lipstick, the app will access your phone’s front camera to scan your face. Using artificial intelligence, it identifies the makeup applied to your face, eyes and lips and assesses the uniformity and boundaries of application and coverage. If there are suggested areas to touch up, the virtual assistant identifies them and makes audible recommendations so you can adjust your look. After your touch up, the app scans your face again and provides feedback on the accuracy of application.

SightSense is an AI accessibility app built for blind and low-vision users who want more than static descriptions. Unlike apps that focus mainly on identifying what’s in view, SightSense is designed for continuous, real-time spatial understanding through live audio and haptic feedback—helping you sense where things are, how far away they are, and how to orient yourself as you move. SightSense is fully compatible with built-in iPhone VoiceOver navigation, and the UI is specifically designed for use with VoiceOver. SightSense recognizes scenes, objects, signs, text, layout, and context, then communicates what’s happening using sounds and haptics. Tailor responses to your preference—from a quick summary to a detailed breakdown—and control everything with simple voice commands or gestures. Navigation Mode describes what’s around you as you move, identifying key landmarks and giving directional clock-face cues for spatial awareness. Text Mode finds and reads print, labels, QR codes, and barcodes, guiding your aim with vibration and sound cues. You can switch modes by voice, gesture, or using VoiceOver. Photo and video descriptions let you capture a moment and hear explanations or ask targeted questions about what’s in the frame. Locate Mode, first of its kind, lets you choose what you want to find—like “door,” “chair,” or “laptop”—and SightSense helps you track it down with increasingly strong haptics, audio cues, and panning audio feedback with earbuds, giving an intuitive “sonar-like” perception of location. Designed with guidance from accessibility organizations and direct feedback from blind and low-vision testers, SightSense supports VoiceOver, adapts to your environment, and includes vibration strength, verbosity, sensitivity, and audio cue controls to match your preferences. Download SightSense and explore the world through your camera lens!