Google’s AI videos get a big upgrade with Veo 3.1

It’s getting harder and harder to know what’s real on the internet, and Google isn’t helping at all with the announcement of Veo 3.1. The company’s new video model is said to offer better audio and realism, as well as greater prompt accuracy. The updated video AI will be available across Google’s ecosystem, including the Flow filmmaking tool, where the new model will unlock additional features. And if you’re worried about the cost of creating all those AI videos, Google is also adding a “quick” variant of Veo.

Veo made waves when it debuted earlier this year, demonstrating a stunning improvement in AI video quality just months after the release of Veo 2. It turns out that having all those videos on YouTube is very useful for training AI models, which is why Google is already upgrading to Veo 3.1 with a host of new features.

Google says Veo 3.1 provides better prompt adherence, resulting in better video outputs and fewer unnecessary calculation cycles. The audio, which was a distinctive feature of the Veo 3 version, is also said to have been improved. Veo 3’s text-to-video conversion was limited to 720p landscape output, but there is an ever-increasing volume of vertical video on the Internet. Thus, Veo 3.1 can produce 16:9 videos in landscape and portrait.

Google previously announced that it would bring Veo video tools to YouTube Shorts, which uses a vertical video format like TikTok. The release of Veo 3.1 likely opens the door to realizing this promise. You can bet that Veo videos will also appear more frequently on TikTok now that they fit the format. This release also keeps Google in the race with OpenAI, which recently released a Sora iPhone app with an impressive new version of its video generation AI.