YouTube Shorts Integrates Veo 2 for AI Video Creation

YouTube Shorts has announced the integration of Google DeepMind's latest video model, Veo 2, enabling creators to generate AI video clips for their content. This new feature allows users to create standalone video clips to enhance their Shorts, expanding on the existing Dream Screen feature that generates AI backgrounds from text prompts.

Veo 2 is Google's answer to OpenAI's Sora, a text-to-video generator. According to YouTube Director of Product Dina Berrada, Veo 2 offers improved understanding of real-world physics and human movement, resulting in more detailed and realistic video outputs. Creators can also specify styles, lenses, or cinematic effects, making it a versatile tool for creative expression.

To ensure transparency, videos created with Veo 2 will be marked using DeepMind's SynthID tool, which watermarks and identifies AI-generated content. This feature is available starting Thursday for creators in the U.S., Canada, Australia, and New Zealand, with plans for broader access in the future.