Google has introduced an impressive feature in its Gemini AI that transforms still photos into 8-second videos with audio, powered by the advanced Veo 3 model. Currently available to Gemini Advanced Ultra and Pro subscribers in India, this tool enhances user experience by adding background noise, ambient sounds, and spoken dialogue. To create a video, users upload an image, describe the desired motion, and optionally include sound prompts. The AI generates a 720p MP4 video in a 16:9 format, synchronizing audio and visuals seamlessly. Videos feature visible ‘Veo’ watermarks and an invisible SynthID for content authenticity. This rollout reflects Google’s commitment to responsible AI deployment amid growing concerns about synthetic media. Users can access this feature via the Gemini web interface first, with mobile support coming soon. With Veo 3, users can expect high-quality visuals that simulate real-world physics and effectively lip-sync dialogue based on prompts. Discover innovative AI tools today!
Source link
