The Uthana Blender add-on brings Uthana’s AI motion generation into Blender. Upload recorded video for markerless motion capture, or type a prompt for text-to-motion, then preview the result and import it straight into your scene.
What It Does
- Video-to-motion — upload footage, get editable 3D skeletal animation back
- Text-to-motion — describe an action and generate it
- Preview results before committing
- Download and import into the Blender scene, then keep editing
The value is staying in Blender. The usual AI mocap loop is browser upload, wait, download FBX, import, fix scale, fix rotation, retarget. Doing it from a panel removes most of those steps.
The Add-on Is Free. The Generation Is Not
Worth being clear about: the add-on itself is a free download from GitHub, but it is a front end to Uthana’s hosted service. It requires an Uthana account, an API key and an internet connection, and generation draws from your pay-as-you-go credit balance.
Current listed rates are $0.10 per second for Text-to-Motion 3.0 and $0.06 per second for Video-to-Motion 3.0. There is no subscription, and credits do not expire.
Requirements
- Blender 4.0 or later
- Uthana account and API key
- Internet connection — nothing runs locally
Install it from the latest GitHub release via Edit → Preferences → Add-ons → Install from Disk, then paste your API key into the add-on preferences.
Cloud vs Local
If you need offline or zero-cost generation, the alternative is a local model. Kimodo Blender Bridge runs text-to-motion on your own machine for free; BlendCap does offline video mocap for a one-off price.
The trade is quality and convenience against cost and privacy — hosted models are generally stronger, local ones keep your footage on your machine.
See also: Uthana Text-to-Motion 3.0 and Video-to-Motion 3.0.
Developer: Uthana · Add-on: Free (GitHub) · Generation: Pay as you go · Requires: Blender 4.0+