Performance driven 2D animation where a camera and a microphone drive a layered puppet in real time, with the full behaviour set, starter puppet library, and live streaming output included.
Overview
The idea behind this application is straightforward and still slightly startling the first time it runs. A layered artwork file is imported, its layers are mapped to a rig, and from then on the webcam drives the head and eyes while the microphone drives the mouth. Perform in front of the machine and the character performs back, recorded live rather than keyframed frame by frame.
Lip sync is the part that carries the whole idea. Speech is analysed into visemes and mapped to the mouth shapes in the artwork, and the result is accurate enough to use without correction for most dialogue. Where it does need a fix, the timeline shows each detected sound as an editable block so a single wrong shape can be swapped without rerecording the take.
Behaviours cover everything the performer is not directly controlling. Physics driven hair, clothing, and dangling props react to head movement automatically, breathing keeps a resting character alive, blinking happens on a natural rhythm, and walk cycles are triggered by moving the character across the scene. Triggers bind keyboard keys to swapped artwork, so hand poses, expressions, and props are changed mid performance without stopping.
Output covers both the recorded and the live case. Scenes render to the usual video formats or hand off to the rest of the Adobe timeline tools through dynamic link, and the live output path sends the performance straight into streaming or conferencing software as a camera source. The package includes the full behaviour set and the starter puppet library, so a character can be performing within minutes of the first launch.
Feature set
Webcam drives head, eye, and eyebrow motion while the microphone drives the mouth, recorded as a live take.
Speech analysed into visemes and mapped to mouth artwork, with every detected sound editable as a block on the timeline.
Hair, clothing, and dangling props react automatically to head and body motion without any manual animation.
Keyboard bound artwork swaps for hand poses, expressions, and props, changed mid performance without stopping the take.
Automatic walk cycles and body movement driven by dragging the character through the scene.
Sends the performance into streaming or conferencing software as a camera source, or renders through the usual export path.
Changes in this build
Installation
Hardware
| Processor | Intel or AMD, 64-bit, quad core with AVX2 |
|---|---|
| Memory | 8 GB minimum, 16 GB recommended for complex puppets |
| Graphics | 2 GB VRAM minimum, 4 GB recommended for live output |
| Storage | 10 GB free space |
| Capture | Webcam and microphone required for performance capture |
| System | Windows 10 version 22H2 or Windows 11 |
Package
| Title | Adobe Character Animator 2026 |
|---|---|
| Version | 26.0.0.50 |
| Developer | Adobe |
| Category | Video Editing |
| Platform | Windows 10 / 11 (64-bit) |
| Package size | 2.16 GB |
| Interface languages | Multilingual (19 interface languages) |
| Release identifier | BS-26000501 |
| Listed | 1 year ago |
| Last rebuilt | 1 week ago |
| Total downloads | 142,485 |
Questions
No. The starter library ships in the package, and layered artwork from the usual raster and vector editors imports and rigs semi automatically.
Any ordinary webcam works. Better lighting improves tracking far more than better hardware does.
Yes. Every captured channel lands on the timeline as editable data rather than a locked recording.
It does, provided the linked applications come from the same release group.
Adobe's flagship timeline editor in its 2026 form, with the rebuilt media engine, caption workflow, and colour management that the studio release ships, packaged to install and open without any account step.
The compositing and motion graphics application, complete with the multi-frame render engine, the 3D workspace, and every bundled effect plugin the studio version installs.
The lightweight editor that took over short form video, in a desktop build with the premium effect library, auto captions, and background removal unlocked and the watermark step removed.
The Studio tier of the grading and finishing suite, which adds the neural engine tools, unlimited resolution, noise reduction, and multi-GPU support that the free version withholds.