Microsoft researchers demoed a new AI framework called VASA-1 that can take in a picture, combine it with an audio clip of any length, and generate a video of the person in the picture lip-syncing to the audio. Read this story
Microsoft researchers demoed a new AI framework called VASA-1 that can take in a picture, combine it with an audio clip of any length, and generate a video of the person in the picture lip-syncing to the audio. Read this story
More from Entrepreneur | Business News News and Trends Artificial Intelligence false