Motion-Omni Provides End-to-End Joint Speech and Body Motion
August 27, 2026
Motion-Omni replaces cascaded speech-to-motion pipelines with a single framework that natively outputs facial expressions and full-body motion from speech hidden states. This joint optimization allows for more coherent spoken dialogue avatars.
HOW THIS AFFECTS YOU
●
builderYou can implement more natural, low-latency conversational avatars using this end-to-end architecture.
●
designerThis enables more expressive and synchronized character interactions in digital environments.