Google has unveiled Veo 3.1, the latest version of its AI video generation model, featuring improved audio output, advanced editing tools, and enhanced image-to-video performance. Building on May’s Veo 3 release, the update delivers more realistic visuals and greater accuracy in following creative prompts.
Veo 3.1 introduces the ability to seamlessly add objects that blend into a scene’s visual style, with object removal capabilities coming soon to Flow, Google’s AI video editor. The model now integrates sound into features like reference-based animation and video extension for more dynamic results.
Veo 3.1 is rolling out across Flow, the Gemini app, and Vertex and Gemini APIs, following the creation of more than 275 million videos on Flow since its May launch.
