Uthana

Uthana is an AI platform for human motion that turns observation and intent into structured 3D movement. It supports generating motion from source video and from text prompts, as well as responsive locomotion driven by direction, speed, and trajectory. The result is editable 3D motion data designed to fit production and training workflows.

Key capabilities include video-to-3D animation, text-to-3D motion, and locomotion generation based on control inputs. Uthana also focuses on “embodiment,” enabling one motion to work across many bodies: motion retargeting transfers movement between different character skeletons, and robot retargeting converts human motion into robot-specific joint representations. Auto-rigging helps prepare unrigged 3D characters for animation without rebuilding motions by hand.

For developers, Uthana provides a single GraphQL API to move from prototype to production. With that API, you can generate motion, extract 3D movement from video, retarget across bodies, and auto-rig characters. It also offers plugins and developer resources (including API docs and quickstart) to help integrate motion generation into your pipeline.

For teams building interactive and simulation experiences, Uthana supports systems that understand how bodies move, including simulated humans that act from goals and environmental context. Pricing is available under the “Pricing” section, and plans depend on usage and features.

What kinds of motion can I generate with Uthana?

You can generate structured 3D motion from text prompts and from source video. It also supports locomotion driven by direction, speed, and trajectory.

Can Uthana convert 2D video into editable 3D motion?

Yes—video-to-motion converts 2D video into animation-ready or training-ready 3D motion data, with delivery formats documented per dataset.

Does Uthana help retarget motion to different characters or skeletons?

Yes. Motion retargeting transfers movement between arbitrary character skeletons, and robot retargeting converts human motion into robot-specific joint representations.

What does auto-rigging mean in Uthana’s workflow?

Auto-rigging prepares unrigged 3D characters for animation automatically, so you can use generated or retargeted motion without manual rig rebuilding.

Is Uthana available for developers via an API?

Yes. Uthana offers motion generation and related capabilities through a single GraphQL API, supporting video motion extraction, retargeting, and auto-rigging.

How does pricing work?

Pricing is listed in the Pricing section, and plans vary based on usage and features.