PKU Releases Motion-Omni for Real-Time Speech-Motion Generation

Peking University's Motion-Omni is an end-to-end spoken dialogue system that generates speech and synchronized full-body gestures in real time (RTF 0.78), using scalable pseudo-labeling to overcome motion data scarcity.

2026-09-07 ~ 2026-09-07 · 3 related posts

• Motion-Omni generates real-time full-body co-speech motion aligned with spoken dialogue — PKU1898 · 2026-09-07
• Peking University's Motion-Omni generates speech and full-body motion in sync, faster than real-time — aigclink · 2026-09-07

1 near-duplicate retellings: aigclink