Google has added photo-to-video capability to its Gemini AI app. Powered by Veo 3, Google’s latest generative video model, launched in May, Gemini AI can now turn images into 8-second videos complete with AI-generated sound including speech, environmental sounds and background noises. Available now via the Web to anyone with a $20 per month Google AI Pro subscription or those on the $125 per quarter Google AI Ultra plan, the new feature is also being released to mobile users this month for both iOS and Android devices. The videos are finished as 720p resolution MP4 files in 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 explains in a blog post. “All generated videos include a visible watermark to show they are AI-generated and an invisible SynthID digital watermark.”

“Gemini users can access the feature by clicking the ‘tools’ option in the prompt bar, selecting ‘video,’ and uploading their photo alongside a text description of how they want it to move,” reports The Verge, adding that “audio descriptions can also be included for dialogue, sound effects, and ambient noise,” which according to Google will sync “perfectly” with the visuals.

TechRadar describes the feature as “pretty incredible,” calling it “easy to use” and noting that “Veo 3’s ability to sync audio to moving images and create videos of your photos from a prompt makes this a welcome addition to the world of AI video generation.”

A similar feature has been available from Google in Flow, the AI storytelling tool launched in March from Google Labs, “but now Gemini users can animate their photographs without having to open another app,” The Verge writes.

When Google launched Veo 3 in May, “it could conjure up a video based only on your description, complete with speech, music, and background audio” with results that Ars Technica calls “staggeringly realistic,” opining that “it’s actually getting hard to identify AI videos at a glance.

“Using a reference photo makes it easier to get the look you want without tediously describing every aspect,” Ars Technica adds, noting that “this was an option in Google’s Flow AI tool for filmmakers, but now it’s in the Gemini app and web interface.”

Concurrent with launching the Gemini AI photo-to-video feature, Google says it is making Flow available in “an additional 75 countries.” Google AI Pro is available in more than 150 countries, Google notes. Since releasing Veo 3, “over 40 million Veo 3 videos generated across the Gemini app and Flow,” according to the company.