Google has added its new AI video generation model Veo 2 to YouTube Shorts, enabling creators to produce AI-generated video clips from text descriptions. As reported by Amanda Silberling for TechCrunch, the feature builds upon the existing Dream Screen capability, which previously only allowed AI-generated backgrounds. The new integration lets users create complete video sequences for their Short-form content. YouTube Director of Product Dina Berrada explains that Veo 2 offers improved understanding of physics and human movement, resulting in more realistic outputs. The system will mark all AI-generated content using DeepMind’s SynthID watermarking technology, making synthetic content clearly identifiable to viewers.
Creators can access the feature through the Shorts camera’s Green Screen option, where they’ll find Dream Screen’s text-to-video interface. The service launches initially in the United States, Canada, Australia, and New Zealand, with plans for broader availability in the future. This development represents Google’s answer to OpenAI’s Sora video generation model, bringing AI video creation capabilities to YouTube’s short-form video platform.