Project AURIONAI Use-Cases Research & Innovation
NVIDIA
avatar

Audio2Face-3D

NVIDIA model that drives realistic 3D facial animation of digital avatars from speech audio.

NVIDIANVIDIAUSA
Figure from the Audio2Face-3D paper: The Audio2Face-3D system receives audio and emotion labels as input and outputs high-fidelity animations for facial skin, tongue, jaw, and eyeballs.
Levelmodel
Classavatar
Parametersnot in the notes
Contextnot in the notes
Released27 Jun 2025
Opennessopen weights restricted
Runs onnot in the notes
Statusactive

R&D Topics

Audio-driven talking heads and lip-syncexemplar

Identity

Developer
NVIDIA
Family
not in the notes
Released
27 Jun 2025 sourcesregistry dateunverified
Weights published
27 Jun 2025
Record checked
12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
not in the notes
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
audio
Output
3D
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
open weights restricted
Licence
NVIDIA Open Model License sources
Access routes
open weights download, API
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Lineage

The notes record no lineage for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. arxiv.org/abs/2508.16401 https://arxiv.org/abs/2508.16401
  2. huggingface.co/nvidia/Audio2Face-3D-v3.0 https://huggingface.co/nvidia/Audio2Face-3D-v3.0
  3. catalog.ngc.nvidia.com/orgs/nim/teams/nvidia/models/audio2emotion_mo... https://catalog.ngc.nvidia.com/orgs/nim/teams/nvidia/models/audio2emotion_model

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Audio2Face-3D", https://aurion.semai.id/models/nvidia-audio2face-3d/, records of October 2026.