Full-body avatar video and voice engine using a diffusion transformer and in-context voice cloning for 1080p expressive video.
- Sep 4, 2025
- —
- textaudiovideo
- —
- —
- 1
Releases
Sep 4, 2025Synthesia releases EXPRESS-2Model release
Synthesia released its full-body avatar video and voice engine with in-context voice cloning and 1080p, 30fps output.