This idea begins with the reading experience of people with aphantasia, who are unable to form mental images, and redefines how digital media interacts with users.

Digital reading environments share one universal behavior: the ability to drag text. This is no different for people with aphantasia. Google Visual Drag focuses on this familiar action within digital reading and introduces a new AI-powered form of interaction. When users drag descriptive text, Gemini generates a video based on the selected content, while the text is simultaneously presented as subtitles.

This technology is designed to work seamlessly across platforms, including mobile and desktop, without limitation. In this process, a simple user action becomes the starting point for an expansion of imagination. AI moves beyond delivering correct answers, transforming abstract language into visual information and responding to each user’s unique way of understanding.