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.
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.
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.
Audio2Face-2D Server Helm Chart is used to deploy Audio2Face-2D Microservice. It automates the steps for push-button deployment to a Kubernetes cluster.
Please refer to the Audio2Face-2D User Guide (under Entities) for more detailed documentation.
By pulling and using Audio2Face-2D software, you accept the terms and conditions of the NVIDIA Maxine Evaluation License Agreement.