Google has unveiled a powerful new feature for its Gemini AI platform, allowing users to transform still photos into dynamic eight-second video clips — complete with AI-generated sound.
Powered by Google’s advanced Veo 3 video model, the new photo-to-video tool brings images to life with synchronized background sounds, environmental audio, and even spoken dialogue.
This update is now available for Gemini AI Ultra and Pro subscribers in select regions, with access rolling out on the web starting today and to mobile devices later this week.
To use the feature, users simply go to the “tools” section in the Gemini prompt bar, select “video,” and upload a photo along with a description of the motion and sounds they’d like to see. The final result is delivered as a 720p MP4 video in a 16:9 landscape format, complete with both visible and invisible watermarks to indicate it was AI-generated.
“You can get creative by animating everyday objects, bringing your drawings and paintings to life, or adding movement to nature scenes,” Google said in a statement.
This technology is similar to what’s offered in Flow, Google’s generative AI filmmaking tool introduced earlier this year. However, Gemini’s integration makes it more accessible — no need to jump between platforms. Google also announced that Flow is expanding to 75 more countries starting today.
Whether for storytelling, social media, or creative experimentation, Gemini’s latest feature gives users a whole new way to animate their imagination.
