Google launches Veo 3.1 AI video generator. Here are the best new features.

While OpenAI's Sora 2 has been getting all the attention recently, we found in our comparison that Google Veo 3 is a more capable video generation model altogether. Now, however, it looks like Google might be widening the gap with the Wednesday launch of Google Veo 3.1.

On top of the basic Veo 3.1 model, there's also a new Veo 3.1 Fast model, which is basically a lighter weight version of Veo 3.1. They're both now available in Gemini, the Vertex AI platform, and Google Flow, the AI video editing tool that's designed around AI-generated videos and editing them together.

So what's actually new with Google Veo 3.1? As you might expect, given the name, it's not necessarily a massive upgrade over Veo 3, which has only been out for a few months now. According to Google, Veo 3.1 offers richer audio as well as better narrative comprehension, which should help ensure that videos make more sense when put in the wider scope of the video. Last but not least, Google says Veo 3.1 offers enhanced realism when it comes to true-to-life textures.

Some of the features available with Veo have been improved too, notably by adding audio capabilities. For example, Ingredients to Video is a feature that lets users upload reference images for Veo to use when creating a video. Users could upload a picture of a character and a location, and have Veo generate a video of the character in that location. This feature is available with audio in Gemini, the Vertex AI platform, and Google Flow, the video editing software that's designed around using Veoo to generate clips to use in a project.

Another feature that's been upgraded with audio is Scene Extension, which essentially allows users to extend a video clip. It's available with audio in the Gemini API, but not the Gemini app. It's also available in Flow.

Another feature is First and Last Frame, which allows users to upload a static image of the first and final frame in a video and have Veo generate a transition between those two frames. It can be used in the Gemini API, Vertex AI, and Flow.

Additionally, Google is adding some precision features to Flow that could help users refine existing video clips. These include the ability to insert or remove objects in a way that looks realistic and natural, though we have yet to test it.

Veo 3.1 is now available in Google Flow, Gemini, and Vertex AI. The other features vary in how widely available they are. You'll need a Google AI Pro subscription to use the new models.