Collection of artifacts related to the NVIDIA AR SDK LipSync Effect

LipSync
The LipSync collection contains the required components to run the NVIDIA AR SDK LipSync effect, which synchronizes lip movements in videos to match target audio containing human speech.
This collection is part of the NVIDIA Augmented Reality SDK.
This model is feature for commercial use. To try out this feature, you must join the Private Access Program. You may request access at Private Access Program.
Technical Details
For detailed model architecture, specifications, training information, and ethical considerations, please visit the LipSync Model Page.
Please note the model included in this feature is a foundation model, trained to work well across various languages. Language-specific fine-tuned models are also available; please contact us for more details.
Installation
To install the LipSync feature:
Download the Augmented Reality SDK Core
To download the SDK Core package:
- Navigate to the Augmented Reality SDK Core Resource
- Choose the appropriate version for your platform, either
<version>_windowsor<version>_linux - Click Download to download the package
Install the Augmented Reality SDK Core and Features
To install the SDK Core and features, navigate to the AR SDK Documentation and follow the installation instructions for Windows or Linux.
To install the LipSync feature using the install_feature.ps1 or install_feature.sh script, use the feature name nvarlipsync.
Try It Out
To try out the LipSync feature, after downloading the SDK and feature, head over to the NVIDIA AR SDK Sample Apps GitHub repository to download and compile the sample applications that demonstrate the LipSync functionality.
Documentation
User Guide: AR SDK Documentation
Terms of Use
The use of NVIDIA LipSync is governed by the following agreements:
- NVIDIA Software License Agreement
- Product Specific Terms for NVIDIA AI Products
- NVIDIA Open Model License
NIM Container
NVIDIA offers a ready-to-deploy NIM container for LipSync. To deploy the NIM container:
docker pull nvcr.io/nim/nvidia/lipsync:latest
For detailed deployment instructions, visit the NIM container page.