Microsoft Research Asia unveiled a new experimental AI tool this week that can create some pretty believable deepfakes.Called VASA-1, the tool can take a still image of a person, or even just a drawing of them, and pair it with an audio file of them to create a lifelike talking face of them almost instantaneously.The tool creates things that look pretty realistic and can mimic things like a person’s facial expressions and head motions from the photo and move their lips in a way that makes it look like they are in fact the one talking – or singing. The group posted some videos of the tool in action that are pretty wild to watchUp close a trained eye can possibly tell that the head motions are a bit robotic, the result of the AI tool is pretty believable. The tool is so believable in fact that the researchers have opted to not release an online demo, API, or product using it until they can be certain it “will be used responsibly and in accordance with proper regulations.”“We are opposed to any behavior to create misleading or harmful contents of real persons, and are interested in applying our technique for advancing forgery detection,” the group said. The group also says that currently videos created with the tool currently have identifiable artifacts.”
Recommended by Our Editors
Ultimately, the researchers see the tool as something that could be used to provide companionship and therapeutic support for people who need it, or used to provide a “person” that someone could talk to in situations where AI is being used.Earlier this week Microsoft took its WizardLM-2 AI model offline within a day of its launch because the developers failed to complete toxicity testing prior to its release.
Get Our Best Stories!
Sign up for What’s New Now to get our top stories delivered to your inbox every morning.
This newsletter may contain advertising, deals, or affiliate links. Subscribing to a newsletter indicates your consent to our Terms of Use and Privacy Policy. You may unsubscribe from the newsletters at any time.
