Dubbing is finally good.

Dubbing is finally good: world models for accurate human presence translate your voice and face together, in real time. Your videos and livestreams in every language; still you.

Until now a dub meant a stranger's voice and a mouth out of sync, because voice and face came from separate tools. One model now generates both together, so the dub stays you. Your voice, your face, in real time.

25 languages, any to any: English, Spanish, Portuguese, Mandarin, Hindi, Japanese, Korean, French, German, Arabic, Indonesian, Russian, Italian, Turkish, Vietnamese, Thai, Polish, Filipino, Tamil, Telugu, Bengali, Czech, Dutch, Greek, and Ukrainian.

We're the first to do voice and face together for dubbing. No one else does; you'd have to stitch ElevenLabs and HeyGen together, and you'd still sound and look like a stranger. Voice sounds closer to you than ElevenLabs + real-time + face; so everything is synced.

Clean, stable footage: podcasts and interviews with 2 or 3 people on camera, videos where you talk straight to the camera, lectures, sermons, presentations. Livestreams are our strongest surface: we dub from your clean camera feed, so quality stays practically untouched. Everyone on camera gets dubbed. Fast cuts, memes over faces, and shaky footage are harder for our current Alpha model; Beta, built to understand the full scene, ships later this year.

Yes; live is our specialty. Stream to your main channel exactly as always; we dub you in real time and push each language's feed to its own channel, 10 to 30 seconds behind. On OBS, our companion app sets everything up in one click. Streaming from a phone: paste our URL as one extra destination, nothing to install. Only you get dubbed; friends and guests stay in their real voices.

Exactly as you say them. You keep a Do Not Translate list: catchphrases, friends' names, signature exclamations. Jokes get rewritten to land in the target language, never translated word for word.

Familiar is a research lab building world models for accurate human presence. Our models understand the physics of a scene and edit the physical world into new scenarios: the face for our Alpha today, progressing toward the full body, object and environmental interaction that is accurate to each person. Our team of 8 brings together researchers from Stanford, HKUST, and Yonsei, including multiple PhDs. For years we've advanced real time diffusion and joint audio visual models while operating international channels for Veritasium, 3Blue1Brown, and Welch Labs. Our newest member is Xu Zheng, Principal Research Scientist, PhD from HKUST, focused on real time diffusion avatars. In his words: “My doctoral research develops robust and interpretable multi-modal learning algorithms spanning perception, understanding, reasoning, and generation.”

Our next version, Familiar Beta, is a world model for accurate human presence. It reads the physics of a scene, even a dozen people speaking on and off screen, game windows, memes, visual effects, and knows who is talking from visual and audio together. Dubbing becomes a physical edit: the model predicts how you would have said it in the new language and renders the performance to match, not just lips but the whole face, with the full body as the goal. First, translation for every video and stream. Then real time meetings, virtual and in person.

For videos, always: the pipeline pauses at a review screen where you edit any line before it renders; credits are only spent then. Live dubs translate on the fly, so there's no review step; your Do Not Translate list still applies.

Join the waitlist. We're letting creators in a few at a time due to limited GPU capacity, and we email you the moment your spot opens.

Free: 4 minutes of video a month, 1 language; no card, ever. Paid starts at $35/mo: 15 minutes of video or 90 minutes of live, all 25 languages, cancel anytime. The first month is the trial.

The dub is yours to post anywhere. At upload you confirm you own the content and consent to us using it to create the dubs and improve future models. That second part is the mission: every dub trains the model that gets us to live dubbed meetings in 2027, in healthcare, courts, classrooms, and families. Billions of people are cut off by language; your dubs help fix that.

No. We only translate you, with your consent. No deepfakes; only translation.

To break every language barrier, virtual or in person. Hundreds of millions can't understand their own doctor, their lawyer, their kid's teacher. We translate people, never fabricate them: your presence carried across, nothing more.