Google unveils Veo 3: Ai model generates videos with synchronized audio

Google has introduced Veo 3, an advanced AI model capable of generating videos from text, at its annual Google I/O event in Mountain View, USA. This new version interprets short stories written by users and transforms them into clips with animations, facial expressions, and audio integrated into the narrative. Veo 3 includes synchronized audio with images, such as dialogues between characters, ambient sounds, and sound effects. This represents a significant advancement over its predecessor, with the ability to understand and transform complex descriptions into realistic scenes with detailed physics, natural movements, and ambient sound. Developed in collaboration with film, music, and visual arts professionals, Veo 3 incorporates SynthID technology to digitally mark AI-generated content, preventing misinformation. Veo 3 is currently available in the United States via the Gemini application for Ultra subscribers and for businesses via Vertex AI. It can also be used on Flow, Google's new platform for AI-assisted film production.