Google Launches Guided Vision in Gemini Live to Provide Real-Time Audio Descriptions via Camera
Guided Vision rolled out October 1 on compatible Android devices, using Gemini Live’s camera feed to read text, identify objects and describe surroundings aloud. It’s also available via TalkBack, but Google says it isn’t for navigation or obstacle detection.
Google launched Guided Vision in Gemini Live on compatible Android devices on October 1, 2026, bringing real-time AI-powered audio descriptions to anything users point their phone’s camera at.
The feature allows users to share their camera feed within the Gemini Live app and receive spoken descriptions of their surroundings. Supported use cases include reading small text, identifying or locating objects, describing surroundings, and detailing specific objects in view. Users can also ask follow-up questions — for example, asking Gemini to read off an expiration date on an item it has already helped locate. If the subject of a query is not in the camera’s frame, Gemini will provide audio cues to help the user align the shot.
Guided Vision is designed primarily for people who are blind or have low vision, as well as those who want assistance in specific situations. Google draws a parallel to Apple’s VoiceOver Live Recognition feature available on the iPhone and Vision Pro. Beyond the Gemini app, Guided Vision is also accessible through Google TalkBack and can be configured as an accessibility shortcut in the Settings app on devices running Android 9 and above.
Google cautions that Guided Vision should not be used for navigation, safe-travel guidance, or obstacle detection, and is not intended as a replacement for a cane or mobility aid.
The feature was previously announced as part of a recent set of Pixel updates before its broader rollout. For users with vision impairments or situational needs, Guided Vision may offer a more accessible way to interact with the physical world through their Android device.