Audio2Face Data Conversion

Use Character Transfer to retarget the animation from the trained Audio2Face model to your own model.

The Audio2Face Data Conversion interface.

This panel is composed of the following widgets:

Common Settings

The Data Conversion tool's Common Settings widget.



Export Directory

Selects a destination for the point cache export.

File Name

Specifies the filename of the exported cache.

Playback FPS

Selects the frames per second you would like the cache to be exported at.

Geometry Cache

The Data Conversion tool's Geometry Cache widget.



Export Filter

Set to export meshes visible in current stage or set to export the selected meshes.


Exports as USD point cache or as a Maya point cache.

Export Cache

Executes the current settings and generates a cache file on disk.

  1. When exporting a custom mesh used in the character transfer process, select the mesh in the stage that is labelled with _result.

  2. When exporting a Maya cache, you can import the source mark head to Maya to assign the cache too. A mark asset (male_head_model_hi_published.mb) can be found in your install directory /audio2face/assets/.

Blendshape Conversion

Use the Blendshape Conversion widget to convert the output Audio2Face animation into a blendshape-driven animation. To use - Set your input animation mesh (The mesh driven by audio2face) and then Set the Blendshape Mesh to connect to and click “Setup Blendshape Solve.”

The Data Conversion tool's Blendshape Conversion widget.



Input anim mesh

The mesh you want to convert into a blendshape animation. It is usually the mesh from the A2F pipeline.

Blendshape mesh

The neutral mesh with blendshape prims and this should be based on the usdSkel schema.

Set up blendshape solve

Setting up an interactive blendshape solve pipeline in the stage.

The Data Conversion tool's Blendsolve nodes in OmniGraph.




Export the resulting blendshape weight values as .json file or USDskelanim.


Check this option to batch export multiple Blendshape Solves.

Additional notes

When exporting animation, you will use the information in “common settings” for the file path and the playback fps.


Now supports Unreal Engine’s MetaHuman via the Omniverse Unreal Engine Connector version 103.1. The exporter creates custom “animation curves” that are imported as an animation sequence to align with the Metahuman skeleton.

Two arrays


This token array contains the names of the control curves, like CTRL_expressions_eyeLookUpR.


this float array contains the time sampled curve value data.

For additional setup options - Select the “BlendShapeSolve” Omnigraph node under the Audio2Face Main Graph node.


Pose & pose option table

When you set up blendshape solve, you can access the pose options:




Name of the blendshape poses.


whether we want to include or exclude the pose in the blendshape solve.

Cancel pair

tagging 2 poses that cancel each other. They cannot be used together at a frame, only one of them can get a non-zero weight.


tagging 2 poses that are symmetric. They try to have the same weights during the blendshape conversion.

Select All, Selection options

(Right mouse click menu): Handy pose selection options.

The Pose Options table.

Toggle use

Toggle the selected “use” checkboxes in the table.

Tag/untag cancel pair

Tag/untag the selected 2 poses as a cancel pair.

Tag/untag symmetry pair

Tag/untag the selected 2 poses as a symmetry pair.

Weight regularization

Stronger value prevents the solve to compute strong weight values. Weight regularization.

Temporal smoothing

Stronger value prevents pops between consecutive frames. Temporal weight regularization.

Weight Sparsity

Stronger value generates sparse blendshape weights, which is preferable for animator’s edit. L1 weight regularization.

Symmetric Pose

Stronger value makes the symmetry poses to have more similar weight values.

Load preset

Load preset blendshape options from a .json file.

Save preset

Save blendshape options as preset in a .json file.

Batch Audio Process

Use the Batch Audio Process widget to export blend weights as .json or .usd for all the audio files within the specified Audio Source Directory.

The Data Conversion tool's Batch Audio Process widget.



Blendshape Weights JSON

Exports blend weights as .json.

Blendshape Weights USD

Exports blend weights as USD.