About Rokoko Vision
Rokoko Vision 3.0 is an AI motion capture tool that turns ordinary video into 3D character animation, with no suit or other mocap hardware required. It now sits inside Rokoko Create, a browser based platform that also offers Text to Motion, and uses a rebuilt solver that works from a single camera.
A user uploads a video of a performer in Rokoko Create, then edits, retargets and cleans up the result in Rokoko Studio. Exports are FBX on every plan and BVH from the Basic plan up, with skeleton options including UE5 Manny, HIK and Mixamo. The page lists Blender, Unreal, Unity, Cinema 4D, Maya, Houdini, MotionBuilder and iClone as compatible. Retargeting to custom characters needs the Basic plan.
It is aimed at creators, artists and previsualization teams who want an accessible way into motion capture. The vendor lists clear limits. Webcam live capture has been removed, dual camera capture is being sunset, and video upload is the route going forward. There is no finger tracking at launch, only one performer can be captured, occluded limbs track less well, and output is post processed rather than real time. The vendor points to its inertial suits for complex motion, real time use and multiple performers.
Pricing as published: Starter is free with 30 seconds of Vision AI processing a month, unlimited text to motion clips and five Studio imports a month. Basic includes 600 seconds of processing a month, 100 Studio imports and unlimited cloud storage, at $10 a month billed annually or $12 a month billed monthly.