Emma Roth is a news writer who covers the streaming wars, consumer tech, crypto, social media, and much more. Previously, she was a writer and editor at MUO.
Google is letting Gemini Advanced subscribers try out Veo 2, its text-to-video AI model that it says is capable of creating high-resolution clips with “cinematic realism.” Starting today, subscribers can select Veo 2 from the Gemini model dropdown on the web and mobile, where they can enter a prompt to generate an eight-second video in 720p.
There’s a limit to how many videos subscribers can create each month, and Google says it will notify users when they approach it. Veo 2 outputs videos in an MP4 format, but users on mobile also have the option to upload them directly to TikTok and YouTube with the “share” button.
Google says the upgraded AI model has a “better understanding real-world physics and human motion,” allowing it to deliver “fluid character movement, lifelike scenes and finer visual details across diverse subjects and styles.” Videos generated with Veo 2 feature SynthID digital watermarks, indicating that they’ve been made with AI.
Along with Veo 2, Google is making Whisk Animate — a tool that lets you transform an image into an eight-second video with Veo 2 — available to Google One AI Premium subscribers. This builds upon Google’s existing Whisk tool, which lets you create AI-generated mashups of images. Whisk Animate is available to subscribers globally through Google Labs.
Google first launched Veo 2 in early access in December, with the tool costing 50 cents per second of video in the company’s Vertex AI platform. YouTube has since added Veo 2 to its experimental Dream Screen feature, which lets users create AI-generated video clips for Shorts.
