NVIDIA Audio2Face is a microservice for animating 3D character's facial characteristics to match any audio track, whether for a game, film, or real-time digital assistant.
NVIDIA Audio2Face-3D is a microservice for animating a 3D character's facial expressions to match any audio track, whether for a game, film, or real-time digital assistant. This repository contains the Audio2Face TensorRT engines, including regression models (claire v2.3.1, james v2.3.1, mark v2.3) and the diffusion model (multi v3.2), optimized for inference across 10 supported NVIDIA GPU platforms.
Model Overview
Description:
Audio2Face-3D generates 3D facial animations from audio inputs, for use in applications such as video conferencing, virtual reality, and digital content creation.
This model is ready for commercial/non-commercial use.
License/Terms of Use
Use of this model is governed by the NVIDIA Open Model License
Deployment Geography: Global
Use Case:
Audio2Face-3D is designed for developers and researchers working on audio-driven animation and emotion detection applications, such as virtual assistants, chatbots, and affective computing systems.
Release Date:
Hugging Face: 08/27/2025 via
https://huggingface.co/nvidia/Audio2Face-3D-v2.3-Mark
https://huggingface.co/nvidia/Audio2Face-3D-v2.3.1-Claire
https://huggingface.co/nvidia/Audio2Face-3D-v2.3.1-James
https://huggingface.co/nvidia/Audio2Face-3D-v3.0
References(s):
NVIDIA, Audio2Face-3D: Audio-driven Realistic Facial Animation For Digital Avatars, 2025.
https://arxiv.org/abs/2508.16401
Model Architecture:
| Audio2Face-3D-v2.3 | Audio2Face-3D-v3.0 | |
|---|---|---|
| Architecture Type | Transformer, CNN | Transformer, Diffusion |
| Network Architecture | Wav2vec2.0 | Hubert |
| Number of Model Parameters | 3.98x10^7 | 1.80x10^8 |
Input:
Input Type(s): Audio
Input Format: Array of float
Input Parameters: One-Dimensional (1D)
Other Properties Related to Input: All audio is resampled to 16KHz
Output:
| Audio2Face-3D-v2.3 | Audio2Face-3D-v3.0 | |
|---|---|---|
| Output Type(s) | Facial pose | Facial motion |
| Output Format | Array of float | Array of float |
| Output Parameters | One-Dimensional (1D) | Two-Dimensional (2D) |
| Other Properties Related to Output | Facial pose on skin, tongue, jaw, and eyeballs | Facial motion on skin, tongue, jaw, and eyeballs |
Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA's hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.
Software Integration:
Runtime Engine(s):
- Audio2Face-SDK
Supported Hardware Microarchitecture Compatibility:
- NVIDIA Ampere
- NVIDIA Blackwell
- NVIDIA Hopper
- NVIDIA Lovelace
- NVIDIA Pascal
- NVIDIA Turing
Preferred/Supported Operating System(s):
- Linux
- Windows
The integration of foundation and fine-tuned models into AI systems requires additional testing using use-case-specific data to ensure safe and effective deployment. Following the V-model methodology, iterative testing and validation at both unit and system levels are essential to mitigate risks, meet technical and functional requirements, and ensure compliance with safety and ethical standards before deployment.
This AI model can be embedded as an Application Programming Interface (API) call into the software environment described above.
Model Version(s):
Audio2Face-3D-v2.3
Audio2Face-3D-v3.0
Training, Testing, and Evaluation Datasets:
Training Dataset:
** Data Modality
- Audio
- 3D facial motion
** Audio Training Data Size
- Less than 10,000 Hours
** Data Collection Method by dataset
- Human - 3D facial motion data and audio
** Labeling Method by dataset
- Human - Commercial capture solution and internal labeling
Properties (Quantity, Dataset Descriptions, Sensor(s)): Audio and 3D facial motion from multiple speech sequences
Testing Dataset:
Data Collection Method by dataset:
- Human - 3D facial motion data and audio
Labeling Method by dataset:
- Human - Commercial capture solution and internal labeling
Properties (Quantity, Dataset Descriptions, Sensor(s)): Audio and 3D facial motion from multiple speech sequences
Evaluation Dataset:
Data Collection Method by dataset:
- Human - 3D facial motion data and audio
Labeling Method by dataset:
- Human - Commercial capture solution and internal labeling
Properties (Quantity, Dataset Descriptions, Sensor(s)): Audio and 3D facial motion from multiple speech sequences
Inference:
Acceleration Engine: TensorRT
Test Hardware:
- T4, T10, A10, A40, L4, L40S, A100
- RTX 6000ADA, A6000, Pro 6000 Blackwell
- RTX 3080, 3090, 4080, 4090, 5090
Ethical Considerations:
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
For more detailed information on ethical considerations for this model, please see the Model Card++ Bias, Explainability, Safety & Security, and Privacy Subcards. Please report model quality, risk, security vulnerabilities or NVIDIA AI Concerns here