Nvidia is letting anyone use its AI voice animation tech
Nvidia has open-sourced its AI-powered tool, Audio2Face, which generates realistic facial animations for 3D avatars based on audio input. The tool works by analyzing the acoustic features of a voice and using that information to create animation data that is mapped to the 3D avatar's facial expressions and lip movement. This allows developers to create realistic 3D characters for their games and apps, including for pre-scripted content and live streams. Nvidia is also making the tool's training frame available, enabling users to customize the models for their specific needs. The change means that developers can now freely use the Audio2Face tool and its underlying framework to enhance their projects.
Source: For the complete article, please visit the original source link below.
