User Interface

Setup

Installation

Unzip and run. Recommended install path. C:/OV/Audio2Face To avoid potential windows issues please keep the install path as short as possible.

To run.

C:/ov/Audio2Face/run_audio2face.bat

Panels

Audio Player

The Audio Player allows you to load custom audio and serves as the primary playback mechanism for Audio2Face

../_images/audio2face_panels_audio-interface.jpg

Option

Description

Audio Source Path

Browse to a folder destination to load all of the audio files within that folder into the “track” menu.

Track

Allows you to select which audio track you would like to playback from your specified library location.

Range

The first box allows you to clip (trim) an audio file to set a desired start time. The second box allows you to clip the audio to specify the end point.

Timeline

A scrubable timeline with play, pause, return to start and loop options.

Allows the setup of the desired source training asset. Nvidia’s Audio2Face asset Loads by default.

Fase Mesh. Selects the character mesh that the network was trained on. Face Material. Offers a choice of materials for the face. Default materials are Grey shaded, Grey shaded with normals detail Basic skin colour map.

Scene Selections

Allows the setup of the desired source training asset. NVIDIA Omniverse Audio2Face asset Loads by default.

../_images/audio2face_panels_data-input.jpg

Option

Description

Fase Mesh

Selects the character mesh that the network was trained on.

Face Material

Offers a choice of materials for the face. Default materials are
Grey Shaded: Grey shaded with normals detail
Basic Skin: Basic skin colour map.

Data Export

Allows the user to export a point cache of the animated mesh.

../_images/audio2face_panels_export.jpg

Option

Description

Export Mesh

Select Which mesh to export a cache from.

Export Directory

Select destination for geom cache export.

File Name

Specifies the File Name

Playback FPS

Select the Frames per second you would the cache to be exported at.

Export As

You have the choice of a USD point cache export or a Maya point cache export.

Pre Processing

Allows the adjustment of key variables that influence the animation result

../_images/audio2face_panels_pre-processing.jpg

Option

Description

Prediction Delay

Specifies how much time the network has to generate a frame.

Input Strength

Allows the user to influence the range of motion of the animation resolve.
Can be mutes for subtle performance or amplified for larger performances.

Post Processing

Allows the user to influence various aspects of the motions resolve as they relate to various regions of the face.

../_images/audio2face_panels_post-processing.jpg

Option

Description

Upper/Lower Face Smoothing

Smooths the motions on the various regions of the face.

Upper/Lower Face Strength

Upper and lower face Strength allows the user to determine the amplification of the motion in these
regions of the face.

Emotion

Allows the user to select a specific face shape from animation training sources to impose on the default face - allowing the user more control to inject specific emotional expressions onto the performance.

../_images/audio2face_panels_emotion.jpg

Option

Description

Source Shot

Selects the animation clip.

Source Frame

Selects the specific frame from the animation source to use as shape of influence.