Nvidia has taught a neural network to animate a 3D model of a face based on voice only. The company began uploading demo videos and training videos in the spring of 2021, and now the open beta version of the program can be downloaded from the company's website. The technology can create animation both on the basis of the finished file and in real time. To do this, you need to load an existing audio track into the application or speak into a microphone. #RandomThoughts