Rokoko Vision is the AI motion capture tool from Rokoko, the Copenhagen-founded company known for its Smartsuit Pro and Smartgloves mocap hardware. Vision brings that expertise to anyone with a video: upload a clip and its AI solver turns the performance into 3D animation data that needs minimal cleanup.
Vision 3.0: rebuilt from the ground up
The latest version, Vision 3.0, features a monocular (single-camera) AI solver rebuilt from scratch to produce much cleaner motion data than the original. Vision now lives inside Rokoko Create, a cloud platform that also includes Text-to-Motion, so you can generate movement from a prompt or capture it from video in the same place.
Edit, retarget and export in Rokoko Studio
Captures import into Rokoko Studio for viewing, editing, smoothing, creating loop segments and retargeting onto characters with custom skeletons. Exports are available as FBX or BVH and are compatible with all major skeletons, including UE5 Manny, HumanIK and Mixamo. Rokoko supports Blender, Unreal Engine, Unity, Cinema 4D, Maya, Houdini, MotionBuilder, iClone and Cartoon Animator.
Affordable entry into professional mocap
A free Starter plan includes 30 seconds of Vision processing per month, and the Basic plan offers 600 seconds per month at a low monthly price. For creators who outgrow video mocap, Rokoko's inertial suits, gloves and face capture provide a direct upgrade path, making Vision a smart starting point among 3D animation generator tools.









