Jev in production › Chat bots and games

motion-engine

Classifies each transcript sentence via Jev to pick facial and body expressions for TalkingHead 3D avatars in real time.

Open on GitHub ↗

The source publishes no measured number.
Use
Chat bots and games
Industry
Media and social
Form
Open-source tool
Stage
Beta
Plugs into
TalkingHead
Listed
2026-10-16
Found via
github
Repository
lhupyn/motion-engine
Stars
36
Forks
3
Last push
2026-10-17
Language
JavaScript
License
MIT

The README opens with

Expressive face and body for TalkingHead avatars, decided by a classifier that reads the transcript — not by tags in the LLM's output.

Live demo — try expressions and gestures right away; add an OpenRouter key to let Jev react to text.

https://github.com/user-attachments/assets/456c9c19-f37a-4aff-8274-5e15c5ce0839

- The main LLM just talks. No emoji, no [happy] markers, no extra rules in its prompt. - Jev decides. Each sentence goes to Jev, TypeSafe's decision model, which picks an expression, a head movement and a hand gesture, each with a confidence. - A director filters. Thresholds, cooldowns and a few rules decide what actually plays. - FACS faces, two body channels. Expressions are Action Unit recipes on ARKit blendshapes that give way to...

Badge

For the project's own README, linking back here:

Listed in Jev in production

Also used for chat bots and games