How Synthesia is combining multiple AI voice and video models to improve avatar realism with natural gestures and accent preservation (Rhiannon Williams/MIT Technology Review)

Wait 5 sec.

Rhiannon Williams / MIT Technology Review:How Synthesia is combining multiple AI voice and video models to improve avatar realism with natural gestures and accent preservation  —  Earlier this summer, I walked through the glassy lobby of a fancy office in London, into an elevator, and then along a corridor into a clean, carpeted room.