Google has introduced an exciting update to its Gemini app: the integration of Veo 3, its advanced video generation model, now enables users to transform a single image into a dynamic 8‑second video, complete with sound.
How It Works
Subscribers to the Google AI Pro and Ultra plans can access the feature via the "Video" option in Gemini’s toolbar. After uploading a photo, users describe the desired motion (for example: camera panning, character movement) and audio elements (like music, ambient sounds, or speech). Within seconds, Gemini generates a 720p MP4 video clip containing both visible and invisible watermarks to ensure transparency.
Availability and Access
Initially released on the Gemini web app, Google plans to roll it out to Android and iOS devices later this week, covering approximately 150 countries. A three-video-per-day creation limit applies, with Pro users getting around 10 monthly videos, while Ultra users can generate up to 5 daily clips.
Why It Matters
This marks a major leap in creative AI democratization, enabling non‑professional users to generate video—not just still images—with minimal effort. The inclusion of SynthID and visible watermarks adds a layer of ethical transparency amid growing concerns about deepfakes and misinformation.
Google’s Veo 3 photo‑to‑video feature brings powerful creative tools directly into the user’s hands, positioning Gemini as a mobile mini film studio.