Google Gears Up with Upgraded Video AI Model Veo 3.1
Google has unveiled its latest artificial intelligence (AI) video generation model, Veo 3.1, featuring enhanced audio output, finer editing controls, and more realistic image-to-video rendering capabilities. The newly released version is an upgrade from Veo 3, introduced in May, offering improved precision in following user prompts, reports TechCrunch.
According to Google, the updated model enables users to “add new objects to a video and automatically blend them into the scene’s original style.” The company added that an upcoming feature in the Flow Editor will allow users to remove unwanted elements from videos.
The previous Veo 3 model supported features such as character control using reference images, generating videos from the first and last frames, and extending scenes beyond the final frame. The latest version now adds audio integration, making videos “more lifelike and dynamic.”
Google announced that the new model is being integrated into the Flow Video Editor, Gemini App, and Vertex and Gemini APIs. Since the launch of Flow in May, users have already created over 275 million videos using the platform.
