New neural network creates an animated 3D model of a face based on a voice

The program runs on the open platform Nvidia Omniverse. There you can make a model in real time.

Available for download on the company's websiteopen beta version of the program. To use the program, you need to load a ready-made audio track into it or use a microphone to record audio directly.

Standard animation uses a Digital Mark character model, but it can be swapped out for a face with any other traits, or even an animal.

The program is now available in English, French, Italian and Russian. The company said that Audio2Face will later be able to handle any languages.

Read more:

Look at pictures of two merging galaxies, taken 9 years apart

A new way of delivering a substance makes cancer cells self-destruct

American scientists received a record energy yield during the experiment