Google has released Veo 2, its text-to-video AI model, to Gemini Advanced subscribers globally. Starting April 15, 2025, users can generate eight-second videos in 720p resolution by entering text prompts in the Gemini app.
The feature, which Google claims delivers “cinematic realism” with improved physics and human motion understanding, is available through a dropdown menu in the Gemini interface. Videos are delivered in MP4 format with a 16:9 aspect ratio, and mobile users can directly share their creations to platforms like TikTok and YouTube Shorts.
Google has also introduced Whisk Animate, allowing Google One AI Premium subscribers to transform still images into eight-second animated clips using the same Veo 2 technology. This builds upon the existing Whisk tool launched in December.
Safety measures
Google emphasizes its safety approach, noting that all videos include SynthID watermarks to identify them as AI-generated. The company has conducted red teaming and evaluation to prevent policy-violating content, though it acknowledges that user prompts primarily determine outputs.
There are monthly limits on how many videos users can generate, with notifications as they approach these thresholds. The rollout is happening gradually over several weeks and supports all languages available in Gemini.
Prior to this consumer release, Veo 2 was available in early access through Google’s Vertex AI platform at 50 cents per second of video, and has been integrated into YouTube’s experimental Dream Screen feature for Shorts.