ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIAKit SDK - Windows (PB25h1)NVIDIAKit SDK - Linux (PB25h1)NVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
NVIDIA
NVIDIA
Audio2Face(A2F) Service
Helm Chart
NVIDIA
NVIDIA
Audio2Face(A2F) Service

UCS application with Audio2Face(A2F) and A2F Controller

NVIDIA Developer ProgramNVIDIA AI Enterprise
NVIDIA AI Enterprise Supported
Join or Subscribe to get accessSubscribe to the product below to access this premium content:
NVIDIA Developer Program
NVIDIA Developer ProgramJoin the Developer Program for access to free tools, support, and tech resources.
Get Access
NVIDIA AI Enterprise
NVIDIA AI EnterpriseAccelerate your AI agent development
Subscribe Now
Note: You can gain access to hundreds more GPU-optimized artifacts by creating a free NGC account.
Already Subscribed?Log in

Please Read! NGC Resource Path Deprecation Warning

Audio2face containers and resources are being moved from the eevaigoeixww/animation/ private registry to nvidia/ace for NGC compliance. This resource is currently still accessible but will be completely removed by the end of December 2024. Please find the new listing at https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ace/helm-charts/a2f-service.

Overview

The Audio2Face Microservice converts speech into facial animation in the form of ARKit blendshapes. The facial animation includes emotional expression. Where emotions can be detected, the facial animation system captures key poses and shapes to replicate character facial performance by automatically detecting emotions in the input audio. Additionally emotions can be directly specified as part of the input to the microservice. A rendering engine can consume blendshape topology to display a 3D avatar’s performance.

The Audio2Face (A2F) Controller Microservice is designed to facilitate the management and integration of the
A2F microservice within larger workflows. It acts as both the origin and the destination of the A2F outputs,
simplifying the interaction with the A2F service by providing a bi-directional API.

Audio2Face Service helm chart contains both Audio2Face Microservice and A2F Controller Microservice.

Getting Started

Please follow the Quick start guide for Prerequisites & dependencies

This helm chart is used as part of the Audio2Face Kubernetes quick deployment script.

Refer to the Audio2Face Kubernetes deployment documentation for more details.

Once Deployed you can use the A2F Controller sample application to send audio data and receive animation data back.

Refer to the Sample application connecting to A2F Controller for more details.

Compatible Infrastructure Software Versions

OS : Ubuntu 22.04 CUDA : 12.1 Driver : 535.54

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.

Getting Help

Enterprise Support
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/

License

By downloading and using this software, you accept the terms and conditions of this license and ACE EULA.

Publisher
NVIDIA
NVIDIA
Latest Version1.0.41
UpdatedDecember 19, 2024 UTC
Compressed Size185.54 KB
Labels
ACENSPECT-BHZI-1M3Y