Quick start

Steps below will help you setup and run the microservice on a Linux system and use our simple sample application to receive blendshapes, audio and emotions.

Prerequisites

This documentation assumes the following system requirements:

OS	Ubuntu 22.04
CUDA	12.1
Driver	535.54

• 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.

NVAIE access

To download Audio2Face Containers and Microservices you need an active subscription to an NVIDIA AI Enterprise product.

Contact a Sales representative on this form and request an access to NVIDIA AI Enterprise Essentials.

NGC Personal Key

Set up your NGC Personal Key if you have not done so already.

Go to the NGC personal key setup page of the NGC website and Generate Personal Key.

Once prompted with a Generate Personal Key form, choose your key Name and Expiration, then select all services for Services Included.

Then you will get your Personal Key, make sure to save it somewhere safe.

You will also need to login to the nvcr.io docker registry, follow the instruction on the same NGC page for that.

Local Container Quick Start

To get started with running Audio2Face microservices the easiest way is to use docker compose.

In the next section, instructions will be provided to run Audio2Face on your machine.

Dependencies

To do so you will need the following dependencies:

• Docker

• NVIDIA Container Toolkit

Once installed, you will need to login to the NGC container registry using the following command

$ docker login nvcr.io -u '$oauthtoken'

You will be prompted for a password which is the NGC API key that you generated earlier.

Running Docker Compose

Clone the repository: https://github.com/NVIDIA/ACE

Go to microservices/audio_2_face_microservice/quick-start subfolder.

Then run docker compose up:

$ docker compose up

It should take a few minutes to boot up the first time and you should see the following output when successful

Creating quick-start_a2f-controller_1 ... done
Creating a2f-init-container           ... done
Creating quick-start_a2f-service_1    ... done
Attaching to quick-start_a2f-controller_1, a2f-init-container, quick-start_a2f-service_1

You are now running a local deployment of the Audio2Face microservice.

To try it out, you can use the sample app provided.