Linux / amd64
NVIDIA Audio2Face Authoring is a component of NVIDIA ACE, delivering real-time face and emotion parameters tweaking using generative AI.
The Audio2Face Authoring microservice is complementary to Audio2Face-3D Microservice. This solution allows you to determine an optimal set of parameters for Audio2Face Microservice.
This microservice supports multiple client simultaneously, enabling workflows that allow many users to connect and generate animation frames at the same time.
Please follow the Quick start guide for Prerequisites & dependencies
Refer to the Audio2Face Authoring documentation for more details.
OS : Ubuntu 22.04 (bare-metal or with WSL)
CUDA : 12.6
Driver : 535.183.06 (for Data Center GPUs), 560.35.03 (for RTX GPUs) and 560.94 (for Windows WSL)
NVIDIA Container Toolkit : latest version
Docker : latest version
NOTE: Any Linux distribution should work but has not been tested by our teams. Some of the newer versions of CUDA 12.x have not been fully tested and may encounter issues during TRT model generation.
Please review the Security Scanning tab to view the latest security scan results. For certain open-source vulnerabilities listed in the scan results, NVIDIA provides a response in the form of a Vulnerability Exploitability eXchange (VEX) document. The VEX information can be reviewed and downloaded from the Security Scanning Security Scanning tab.
Evaluation preview does not currently offer support. For Enterprise customers, please use Enterprise Support to get access to knowledge base articles and support cases or submit a ticket: https://www.nvidia.com/en-us/data-center/products/ai-enterprise-suite/support/
This software is governed by the NVIDIA Software License Agreement and Product Specific Terms for AI Products. Use of the models is governed by the NVIDIA Community Model License.
By downloading and using this software, you accept the terms and conditions of this license, the evaluation agreement in this license, and ACE EULA.