Generate realistic lip sync and facial animation from audio using NVIDIA Audio2Face. Works offline in Unity Editor and Windows runtime, supports ARKit blendshapes and AnimationClip creation.YOUTUBE | DOCUMENTATION | SUPPORTAudio Face Animator is a Unity plugin that automatically generates realistic facial animation from audio files using the NVIDIA Audio2Face AI model.The plugin analyzes speech and produces synchronized facial movements driven by ARKit-compatible blendshapes, making it easy to animate characters.FeaturesGenerate facial animation directly from audio files.Powered by NVIDIA Audio2Face AI technology.Fully offline processing — no internet connection required.Accurate audio-to-animation synchronization.Uses ARKit blendshapes for facial animation.Emotions: drive a clip through a sequence of emotions - anger, joy, fear, sadness, amazement, cheekiness, disgust, grief, pain, out of breath - each with its own share of the clip, intensity and crossfade. Ready-made presets included.Audio-driven eye motion, applied to your character's eye bones, with an optional Look At target blended on top.Procedural blinking generated in Unity and mixed into the performance, with full control over timing and amplitude.Flexible mapping: one expression can drive several blendshapes and several bones at once, so characters without a complete ARKit set are supported. Auto-mapping by name, in-editor preview, and mapping presets you can reuse across characters.Fine-tune the model itself: face strength and smoothing, face mask, eyelid and lip offsets, eye and saccade strength, and more.Create and save Unity AnimationClips - blendshapes, bones, eyes and blinks are all baked into the clip.Works inside the Unity Editor.Supports runtime generation in Windows Standalone applications.IncludedThree ready-to-use sample characters, a sample scene, voice samples and emotion presets - everything you need to see it working before touching your own character.RequirementsUnity 6000.0 or newer.Windows 10 / 11, 64-bit.NVIDIA GPU, compute capability 7.5 or newer — GeForce RTX 20-series or newer, or the equivalent Quadro / RTX A-series / data-center card. AMD and Intel GPUs are not supported.NVIDIA driver 576 or newer. CUDA and TensorRT are bundled with the plugin; nothing has to be installed separately.6 GB or more free VRAM while generating.About 3 GB of disk space, and roughly the same again while the plugin copies its model files into StreamingAssets.Character model with ARKit blendshapes, or with bones you map to the ARKit expressions.Getting startedImport the package. The Preflight Check opens and tells you whether your machine can run the plugin.Follow the two buttons in it: sync the model data, then build the engine for your GPU. The build takes about a minute and happens once per machine.Open the sample scene, enter Play Mode, press Generate. For your own character: add Face Animator, map the blendshapes, assign an AudioClip.Audio Face Animator provides a fast and efficient workflow for creating expressive facial performances from voice recordings without manual keyframing.───────────────────────────────MORE FROM DEVELOOPWant to try it first? Audio Face Animator Lite is free:https://assetstore.unity.com/packages/slug/383626All our Unity tools and animation packs:https://dev-eloop.github.io/Support: dev.eloop@outlook.comSupported Platform: Windows (Editor and Standalone)GPU Requirement: NVIDIA, compute capability 7.5+ (RTX 20-series or newer), driver 576+Processing Mode: Local/offline onlyAI Model: NVIDIA Audio2FaceFacial Rig: ARKit blendshapesInput Format: WAV or Unity AudioClip — converted to 16 kHz mono automaticallyOutput: Real-time blendshape animation and Unity AnimationClipsAudio Face Animator uses Nvidia's Audio2Face model to generate facial animations from audio.
