NVIDIA
NVIDIA
Audio2Face-2D Microservice
Collection
NVIDIA
NVIDIA
Audio2Face-2D Microservice

Audio2Face-2D Microservice animates a person's portrait photo using a driving audio. This collection features containers, resources, and helm charts

Subscribe to get accessSubscribe to the product below to access this premium content:
NVIDIA Maxine Early Access
NVIDIA Maxine Early AccessNVIDIA Maxine Early Access is currently available by request only. Please submit a request to learn more.
Note: You can gain access to hundreds more GPU-optimized artifacts by creating a free NGC account.
Already Subscribed?Log in
Subscribe Now

Audio2Face-2D Microservice

Audio2Face-2D, also known as Speech Live Portrait, animates a person's portrait photo using a driving audio. It also accepts tuning values to control eye blinks, head movement, and gaze of the portrait animation. Maxine Audio2Face-2D Server is a Docker image containing end-to-end applications with necessary dependencies that can be easily deployed on public and private clouds and enable client applications to provide the benefits of NVIDIA Maxine Audio2Face-2D algorithms via cloud-based GPU computing.

What is included in the Audio2Face-2D Microservice collection?

Containers (under Entities)

Audio2Face-2D Server is a Docker image containing end-to-end applications with necessary dependencies that can be easily deployed on public and private clouds and enable client applications to provide the benefits of NVIDIA Maxine algorithms via cloud-based GPU computing.

Audio2Face-2D Client is a Docker image containing a sample command-line application for Audio2Face-2D Microservice. The Client expects that an Audio2Face-2D server is running. A GPU is required to run the sample client. Audio2Face-2D Client connects to the microservice configured and running on the Audio2Face-2D Server, sends audio to process to the server, and receives the processed video and audio back from the server.

Resources (under Entities)

Audio2Face-2D Quick Start Guide contains information to help you get started with setting up and running the Audio2Face-2D Microservice.

Audio2Face-2D Reference Client is an example of a client application (in source code format) available in multiple programming languages. This can be used as a reference for creating custom applications for connecting to the Audio2Face-2D service.

Audio2Face-2D User Guide is a detailed user guide for reference by developers.

Helm Charts (under Entities)

Audio2Face-2D Server Helm Chart is used to deploy Audio2Face-2D Microservice. It automates the steps for push-button deployment to a Kubernetes cluster.

Documentation

Please refer to the Audio2Face-2D User Guide (under Entities) for more detailed documentation.

License

By pulling and using Audio2Face-2D software, you accept the terms and conditions of the NVIDIA Maxine Evaluation License Agreement.

Audio2Face-2D Microservice
Publisher
NVIDIA
NVIDIA
UpdatedMarch 14, 2025 UTC

NVIDIA uses cookies to improve your experience on our web site. We and our third-party partners also use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings." By continuing to use this site or by clicking one of the buttons below, you agree to our Terms of Service (which contains important waivers). Please see our Privacy Policy for more information on our privacy practices.