Google wants you to take a break from OpenAI's Sora and try out its new AI video model. The newest version of its flagship AI video generator is here, named Veo 3.1, the company announced Wednesday. Veo 3.1 is available now for paying Gemini users and through Flow, the Gemini API and Vertex AI.
The new version of Veo will have some features you may recognize if you've used Flow, Google's AI filmmaking program. Ingredients to video will let you upload separate assets that Veo will combine in the final video, which first debuted on Flow. You'll also be able to add objects to existing assets, with the much-needed ability to remove objects coming soon.
You can now also give Veo a starting and ending still shot, and it will generate an AI transition to blend the two images into a short video clip. Short clips can now be extended to be over a minute long, another way to smooth out transitions between clips. These transition tools will be helpful for creators, as AI video has previously relied on many hard jump cuts between short clips.
Watch this: How to Use Google's Veo 3 AI Video Generator: It Helped Me Produce This Video 05:50
Google's Veo 3 dropped earlier this year at its I/O developers conference and quickly found fans. It was the first AI video generator to include native, AI-generated synchronized audio. Google has been investing heavily in generative media this year. Its nano banana AI image model quickly gained popularity. But Google's dominance has been challenged by OpenAI. The ChatGPT maker dropped a new version of its AI video generator, Sora, and created a TikTok-like social media app. Sora has been the topic of much debate, with enthusiasts eagerly snatching up invite codes and, more concerningly, experts worried about its ability to create convincing deepfakes and further fill the internet with AI slop.
AI video generators like Veo and Sora highlight the controversial role generative AI plays in creative industries. Many videographers, filmmakers and creators are concerned about how AI is trained on their existing material and deployed by studios and streamers. While hotly contested debates rage on, many artists and authors are taking AI companies to court over alleged copyright infringement and other intellectual property issues. (Disclosure: Ziff Davis, CNET's parent company, in April filed a lawsuit against OpenAI, alleging it infringed Ziff Davis copyrights in training and operating its AI systems.)
For more, check out what to know about video generators and the best AI image generators.