Google has integrated the AI model Veo 2 for video generation into Gemini for users with a Gemini Advanced subscription.
Dive into video creation with @GeminiApp — rolling out today.?
Transform text prompts into cinematic 8-second videos with Veo 2 in Gemini Advanced. Select Veo 2 from the model dropdown menu to get started.
Prompt: Write the word “GOOGLE” out of skydiving parachutes opening up pic.twitter.com/IHTmhELUut
— Google (@Google) April 15, 2025
Users can select the neural network from the list of available models in the Gemini apps. It allows the creation of eight-second videos with a resolution of 720p and a 16:9 aspect ratio. The results can be shared on TikTok, YouTube, and other platforms or downloaded in MP4 format with watermarks added.
The company has set monthly limits on the number of videos that can be generated.
Additionally, Veo 2 is integrated into Whisk — an experimental feature in Google Labs that enables video creation based on an image.
Google introduced Veo 2 in December 2024.
Earlier in April, AI startup Runway released a new series of video generation models, Gen-4. These models can maintain scene integrity and character appearance across multiple frames.