EmbodyMe Launches Voice2Face Technology

Tokyo-based EmbodyMe has added Voice2Face technology to its xpression camera app.

Created for video meetings, live streaming, and chatting, xpression camera is a real-time, face-filtering app that lets users be off camera while the app fully animates their images on screen. xpression camera depicts users' facial expressions on any face-featured photo, and the animation can be driven by either the user's voice or by looking at the screen.

"Our new proprietary AI gives users even more flexibility. You like to pace while on a video call - no problem. Let your voice drive your image on screen. Your facial features are naturally animated, but you don't need to be stuck staring at the screen," said Issay Yoshida, CEO of EmbodyMe, in a statement.

Now with xpression camera's Voice2Face technology, the creator's face and/or voice becomes the blueprint to instantaneously maneuver expressions, as well as the facial and head movements in a chosen photo on screen. EmbodyMe uses neural rendering and 3D Dense Face-Tracking to capture facial movements in real time and regenerate visual elements immediately.

xpression camera also lets content creators import videos or stream live in Zoom, Twitch, Microsoft Teams, Google Meets, YouTube, and more. Creators can become any image with a face, including pictures, paintings, stuffed animals, dolls, artwork, comics, cartoons, sculptures, illustrations, pets, or stars in movie or TV clips.