Google has launched a new photo-to-video feature for paying Gemini users, letting them turn still images into 8-second MP4 videos with sound. Available from 12th July via the web for Google AI Pro and Ultra subscribers in select regions, the feature will roll out to the Gemini mobile app this week.

Users can upload a photo, add a short prompt describing the desired animation and audio, and the tool will generate a 720p landscape video using Google’s Veo 3 model.

Unveiled at Google I/O in May, Veo 3 has already powered over 40 million videos. The new feature brings these capabilities into Gemini’s chat interface, helping Google compete with tools like OpenAI’s Sora and platforms from Alibaba and Kuaishou.

To use it, users select “Videos” in Gemini’s prompt bar, upload an image, and describe the animation. It works best with objects, artwork, and nature scenes, but struggles with complex actions and realistic facial animation. Google said improvements are underway.

IT Stocks Insights? Let the Analyst Guide You.

Unlock profitable opportunities every day! Unicorn Signals provides actionable intraday trading signals for stocks and futures. Don’t miss out – download Unicorn Signals and start winning now!