Google Expands Access to Veo 2 Video Generation Model

After a limited, four-month preview, Google is now making its Veo 2 video generation model available to a broader audience. The company has started rolling out the tool to Gemini Advanced users, enabling them to create 720p clips that are up to eight seconds long. As Google notes, “The more detailed your description, the more control you have over the final video.”

Initially, Gemini will only generate footage in 16:9 landscape orientation, which may not be ideal for creating social videos. However, Google points out that users can upload videos directly to TikTok or YouTube through Gemini’s share sheet, and any footage created through the chatbot will automatically be formatted as an MP4 file. Compared to its predecessor, Google says Veo 2 has a better understanding of real-world physics and human motion.

To start using Gemini to generate video clips, users will need to subscribe to Google’s $20 per month One AI Premium Plan. Once the rollout of Veo 2 is complete, video generation will be available in every language supported by Gemini, both on the web and mobile. Additionally, Google is integrating Veo 2 generation into Whisk, an experimental AI application available through the Google Labs beta platform, which allows users to generate images from text and image prompts and now animate their creations with Veo 2.