Google’s Gemini AI Now Turns Photos into Videos with Realistic Audio

Google has introduced a new feature for its Gemini AI that lets users transform still photos into short video clips, complete with AI-generated audio. The new photo-to-video tool is powered by Google’s Veo 3 video model, which can turn reference images into eight-second videos with added background sounds, environmental effects, and even speech.

The update is now available for Google AI Ultra and Pro subscribers “in select regions,” according to the company. It has started rolling out on the web today and will reach mobile devices later this week.

To use the tool, Gemini users simply click on “tools” in the prompt bar, select “video,” and upload a photo with a description of the desired animation. They can also include details for dialogue, ambient noise, and sound effects, which Google says will be “perfectly synced with the visuals.” Finished videos are delivered as MP4 files in 720p resolution and a 16:9 landscape format. 

“You can get creative by animating everyday objects, bringing your drawings and paintings to life, or adding movement to nature scenes,” Google said. “All generated videos include a visible watermark to show they are AI-generated and an invisible SynthID digital watermark.”

A similar capability already exists in Flow, Google’s generative AI filmmaking tool launched in March. But now, Gemini users can animate photos directly within Gemini without needing to switch apps. Google also announced that Flow is expanding to “an additional 75 countries” alongside the new Gemini video feature rollout.