Familiar

What it does

🦋 Content in every language. The speakers' performances, preserved. Movies & TV, Broadcasts, Education, Ads, Platforms, Live Shopping. Founders An Zhu Liu, Mingi Kwon, and Xu Zheng lead a team of PhDs, professors, and researchers from the world's top universities who started the field of joint audio-visual human models and co-authored the current state of the art in real-time human animation. They started with video language translation, and they've already built one of the most accurate translators available today, the only one that works in real time. Everyone else scaffolds separate models and pre-processing; a world model just understands -- what the speaker means, from voice, person, and scene together. That's why the dub keeps the speaker's own voice, face, and delivery. Vs ElevenLabs: they lose the laughter, the music, the ambiance -- 270% more background-sound error -- and ours sounds 27.8% more like you. Vs human translators: 100.3% of their quality -- scalable, real time. Published benchmarks: https://thefamiliarlab.com/benchmark The $14B spent on dubbing every year flips to AI once it's good enough -- most of it movies and TV, the traditional dubbing heartland. Live multiplies it.