The functionality mirrors Apple’s VoiceOver Live Recognition, providing a verbal bridge between physical objects and digital accessibility. Beyond simple identification, users can engage in a back-and-forth dialogue with the AI to extract specific details, such as checking an expiration date on a food package. If an object is framed incorrectly, the system provides audio cues to help the user adjust their camera angle.
Integration extends beyond the standalone Gemini app, as the feature is now baked into Google TalkBack. Users on devices running Android 9 or newer can also map the tool to an accessibility shortcut in their settings. Despite these capabilities, Google explicitly warns against using Guided Vision for high-stakes tasks like navigation, obstacle detection, or as a primary replacement for traditional mobility aids like canes.

Comments (0)
No comments yet. Be the first!