Synthesia’s new Expressive Avatars prove digital actors are getting more and more convincing.
One of Synthesia’s Expressive Avatars.
Artificial intelligence (AI) video generators and the avatars they create are evolving quickly and UK-based AI video company Synthesia hopes to take the emerging technology to the next stage.
On Wednesday, the company announced its Expressive Avatars, which can depict a range of lifelike human emotions. The latest edition of what the company calls its « digital actors », the Expressive Avatars feature enhanced facial expressions, more accurate lip sync, and realistically human-like voices — an upgrade from the robotic tone of most text-to-audio AI.
« This technology brings a level of sophistication and realism to digital avatars that blurs the line between the virtual and the real, » the company said in the announcement.
Synthesia’s text-to-video platform comes with more than 160 stock AI avatars users can choose from, which the company created based on human actors, with their consent and compensation. Teams can collaborate on videos from end to end and create videos in more than 130 languages.
The company aims to replace the entire video production process with their software — but they’re not coming for Hollywood, CEO Victor Riparbelli said during a demonstration of the release. Instead, the company focuses on enterprise and B2B content, where it sees a requirement for easy-to-create, engaging, and human-like video.
Synthesia’s Expressive Avatars are powered by its Express-1 AI model. While the company uses open-source LLMs for the text elements of the product, Express-1 was trained entirely on content Synthesia produced in-house — nothing synthetic or scraped from the web.
