Photo by Charlotte May on Pexels

Google’s Gemini AI is expanding its creative capabilities with a new feature that turns static photos into short, dynamic video clips. Powered by the Veo 3 video model, this update allows Google AI Ultra and Pro subscribers in select regions to transform images into eight-second videos, complete with AI-generated audio. The audio includes ambient sounds, environmental effects, and even generated speech.

Accessible through the “video” option in the Gemini prompt bar, users simply upload a photo and provide a text description to guide the animation. Detailed instructions for motion and audio, including dialogue and sound effects, can be specified. The final product is a 720p MP4 video in a 16:9 landscape format.

Google suggests users can animate everyday objects, breathe life into artwork, or add movement to natural scenes. To ensure transparency, all generated videos feature a visible watermark and an invisible SynthID digital watermark identifying them as AI-generated. This feature was previously available in Google’s Flow filmmaking tool, but the integration within Gemini provides broader access to this innovative functionality.