Express-2

Synthesia's next generation, announced 19 Aug 2025: voice cloning (Express-Voice) plus a diffusion-transformer video stack (Express-Video, made of Express-Animate, Express-Eval and Express-Render). Produces full-body gesturing avatars in 1080p 30fps video of arbitrary length. Available to paying customers; Express-1 is not retired.

Understands

text, audio

Produces

video, speech

Contents verified with the vendor: 2026-08-18

Included in subscriptions

No catalogue entry marks this model as part of a plan yet. It will appear here once the plan contents are confirmed with the vendor.