Google’s AI videos are getting a major upgrade with Veo 3.1

It’s becoming increasingly difficult to know what’s real on the Internet, and Google isn’t helping one bit announcement of Veo 3.1. The company’s new video model is believed to offer better audio and realism, along with greater accuracy. The updated video AI will be available across the Google ecosystem, including the Flow filmmaking tool, where the new model will unlock additional features. And if you’re worried about the cost of calling up all these AI videos, Google is also adding a “fast” variant of Veo.

Veo made waves when it debuted earlier this yearwhich shows a stunning improvement in AI video quality just a few months after the release of Veo 2. It turns out that having all those videos on YouTube is very useful for training AI models, so Google is already moving to Veo 3.1 with a whole bunch of new features.

Google says Veo 3.1 offers stronger fast compliance, resulting in better video output and fewer wasted compute cycles. Audio, a feature of the Veo 3 release, has also reportedly been improved. Veo 3’s text-to-video was limited to 720p landscape output, but there is an increasing volume of vertical video on the Internet. Veo 3.1 can therefore produce both landscape and portrait 16:9 video.

Google previously said it would add Veo video tools YouTube shortsthat use a vertical video format like TikTok. The release of Veo 3.1 likely opens the door to making that promise a reality. You can bet that Veo videos will appear more often on TikTok now that it fits into 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-generating AI.