US Patent and Trademark Office announcements or Microsoft's official publications

Microsoft's VASA-1 AI Creates Real-Time Hyper-Realistic Talking Faces, Sparks Regulatory Talk

Apr 18, 2024, 05:08 PM

Microsoft Research has unveiled VASA-1, a groundbreaking AI model capable of generating hyper-realistic talking face videos from just a single portrait photo and speech audio in real time. This technology ensures precise lip-audio synchronization, lifelike facial expressions, and naturalistic head movements. The AI's ability to create such high-quality deepfake videos has sparked discussions about the potential need for regulatory action due to its implications for creating believable digital personas.