- Google announced Veo 3 at its annual I/O developer conference, enhancing AI-generated video with synchronized audio.
- The model generates photorealistic video and ambient sounds, including human voices, based on natural language prompts.
- Veo 3 specializes in simulating real-world physics and lip-syncing, making it a valuable tool for filmmakers.
- The fusion of AI-generated video and audio has been a significant technical challenge in the AI industry.
- Veo 3 is available for Gemini Ultra subscribers in the US and can be accessed through Google’s new filmmaking tool, Flow.