London-based AI-startup Synthesia, which creates avatars for enterprise-level generative video presentations, has added “Expressive Avatars” to its feature kit. Powered by Synthesia’s new Express-1 model, these fourth-generation avatars have achieved a new benchmark in realism by using contextual expressions that approximates human emotion, the company says. Express-1 has been trained “to understand the intricate relationship between what we say and how we say it,” allowing Expressive Avatars to perform a script with the correct vocal tone, body language and lip movement, “like a real actor,” according to Synthesia.

VentureBeat points out that Synthesia’s announcement “comes just a week after Microsoft showed off VASA, an AI framework that converts human headshots into talking and singing videos, complete with expressions and head movements.”

But unlike VASA, which is at this point a research effort, Synthesia’s Expressive Avatars technology is available for commercial use now, “and will help Synthesia’s customers create more realistic AI videos than ever for their target audiences,” VentureBeat reports.

Synthesia explains in a blog post that since 2017 it has been on a mission to “transform any employee into a video creator,” by building a user-friendly enterprise platform “for business communications and knowledge sharing.” In that time, more than 200,000 people have used their technology, resulting in use of its 225 off-the-shelf avatars in over 18 million video presentations published in about130 languages.

MIT Technology Review says the Expressive Avatars release “means almost anyone will now be able to make a digital double,” describing a trip to Synthesia’s London office to get scanned as a “data collection process” to capture “facial features, mannerisms, and more.” The result, the author says, is “a hyperrealistic deepfake of me that’s so good it’s scary.”

Founded by “a team of AI researchers and entrepreneurs, including some from Stanford and Cambridge Universities, Synthesia has built an end-to-end platform to create custom AI voices and avatars (users can even use existing ones) and use them with pre-written or AI-produced scripts to generate studio-quality AI videos,” writes VentureBeat.

TechCrunch describes the company’s focus as “custom avatars designed for business users to create promotional, training and other enterprise video content,” and says the this latest update features avatars “built based on actual humans captured in their studio,” which results in “more emotion, better lip tracking and what it says are more expressive natural and human movements when they are fed text to generate videos.”