Veo is Google's new AI video generator, and its answer to OpenAI's Sora

Google I/O is upon us, and AI is a big focus for Google for very obvious reasons. Alongside other tools, Google has just launched Veo, it’s most capable generative video model that takes on the likes of OpenAI‘s Sora and RunwayAI.

Google says Veo can create high-quality 1,080p clips that go beyond 60 seconds using text, image, or video prompts.

It can also tackle a range of cinematic styles, such as photorealism, surrealism, and animation. It also has an understanding of natural language, which allows the model to understand cinematic terms like “timelapse” and “aerial shots of a landscape.”

The videos generated through Veo are also said to be more consistent and coherent, depicting more realistic movement and continuity throughout the shots.

Another highlight ability of Google Veo is that it allows you to easily extend a generated video with the click of a button.

Further, the generated video results can be refined using additional prompts. Google is also exploring additional features enabling Veo to produce storyboards and longer scenes.

Google Veo will be available to select creators later this year, and waitlist sign-ups are now open. However, sign-ups are limited to certain areas. Google is planning to add some of Veo’s capabilities to YouTube Shorts in the future, though it remains anyone’s guess how that will turn out.