Google’s Veo 3.1 Brings Sound and Enhanced Editing to AI Video Generation
Google has released an updated version of its AI video generation model, Veo 3.1, building on the capabilities of the initial “I see 3” model introduced in early July. The new iteration focuses on creating more realistic and user-controlled video content, now incorporating sound and offering more precise editing features.
A key advancement in Veo 3.1 is the ability to transform uploaded images into videos with accompanying sound effects – a feature previously unavailable. this allows the AI to generate complete videos incorporating visuals, motion, and audio that adhere to realistic physics.
Beyond sound, Veo 3.1 enables users to seamlessly add or remove objects within videos, with the AI intelligently integrating them into the scene.The “Frame to video” function allows for the creation of videos using custom opening and closing frames,filled with AI-generated content for the middle portion. Users can also leverage AI to extend existing video footage.
