Transform static photos into dynamic videos with Google’s Gemini AI. This new feature adds sound and animation, opening up endless creative possibilities!
Google has just unveiled an exciting new feature in its Gemini AI app that is set to pique the interest of creators, enthusiasts, and other curious users. Gemini AI users can now transform their still photos into eight-second video clips with audio, thanks to the Veo 3 video generation model.
This new tool, which is available to Google AI Ultra and Pro subscribers in select regions, rolls out initially on the web version of Gemini, with mobile app support arriving shortly after. For Pro subscribers at $20 per month (three video generations per day) and Ultra subscribers at $250 per month (five video generations per day), users can take their photos and give them a narrative twist.
All they need to do is upload an image, choose the “video” option from the Gemini prompt bar, and describe the kind of animation and audio they want the image to carry—whether that’s sound effects, dialogue, or an entirely new scene.
The video outputs are generated in 720p MP4 format and have a standard 16:9 aspect ratio, so they can be easily shared or incorporated into various projects.
While Google is expanding Gemini’s capabilities, it’s not the first to explore photo-to-video technology. The company’s Flow tool, introduced in March 2025, already includes a similar feature for generative filmmaking. However, this new addition to Gemini brings the ability to animate photos directly within the app, making it more accessible to casual users without the need for a separate tool.
Of course, with great innovation comes great responsibility. Google has incorporated multiple safety measures to combat potential misuse of the new video tool.
Google said that “all generated videos include a visible watermark to show they are AI-generated and an invisible SynthID digital watermark."
Furthermore, the technology restricts the creation of videos from images of identifiable public figures or content promoting violence, bullying, or any harmful behavior.
In the context of an increasingly competitive space for AI video generators, Gemini’s photo-to-video feature sets Google apart from rivals like OpenAI, Runway AI, and other global players like Alibaba and Kuaishou Technology. The ability to animate photos within the same app that generates other forms of content provides a unified creative experience that appeals to a wide range of users, from professionals to hobbyists.
Ultimately, this new feature is a game-changer for anyone wanting to experiment with visual storytelling. Whether you’re an artist, a content creator, or just someone curious to see what their photos can become, Google’s Gemini AI is opening up new creative avenues, making it easier than ever to turn your still images into animated works of art.
