Familiar is the Neolab for world translation. Dubbing into 30 languages. Something impossible for humans -- now with Familiar, the same actor's performance, preserved instead of a mismatched voice over a mismatched face. One model does the voice, the lips, and the scene together, with identity permanence and 3d understanding; and it matches human translators, published. Built by the researchers who pioneered joint audio-visual human models. thefamiliarlab.com/benchmark