Overview

../_images/audio2face_introduction.jpg

Overview

Audio 2 Face is a combination of AI based technologies that generates facial motion and lip sync that are derived entirely from an audio source. Audio2Face offers various ways to exploit the technology – it can be used at runtime or to generate facial animation for more traditional content creation pipelines.

The Early Access release available in September 2020 is intended primarily for advanced users willing to work with a limited complement of GUI features, documentation and tutorials. This early access preview version primarily aims to demonstrate the core functionality of the application. The next release will enable robust tools to allow the user to drive their own custom meshes and employ Audio2Face in a production pipeline or runtime projects.