FAMILIAR ALPHA

Demos

The demos on the home page

Previous demos

Movies & TV
Korean
Spanish
FAMILIAR
VS
SYNC.SO

Sync.so, the industry's best standalone lip-sync: $8 a minute for the visual side only, no translation, no voice. With several people on screen, it moves every mouth at once.

George Janko
ORIGINALFAMILIAR

Mics over the mouth, hands across the face: the dub holds.

Japanese · Spanish
Korean
7 PEOPLE SPEAKING
FAMILIAR
VS
SYNC.SO

Sync.so, the industry's best standalone lip-sync: $8 a minute for the visual side only, no translation, no voice. With several people on screen, it moves every mouth at once.

Arabic
Arabic
Chinese

SAME CLIP · ENGLISH → KOREAN

THE ORIGINAL
ENGLISH

Original

The set as he performed it, in English.

STILL HIM
KOREAN
FamiliarDubbed

Dubbed. Side angles, fast movement, the same performance in Korean: still sounds like him, still looks like him.

SAME CLIP · KOREAN → ENGLISH

STILL YOU
ENGLISH
FamiliarDubbed

Your voice, lips, and scene sound, carried into new languages; delivered up to 4K with a true 5.1 surround or stereo mix.

VS
CURRENT INDUSTRY LEADERS
NOT YOU

HeyGenElevenLabs

Doesn't sound like you, doesn't look like you: lighting, moustache, hands… HeyGen V3 for visual + ElevenLabs for voice (these are the largest companies in dubbing, worth billions).

▚ TESTED ON THE SAME CLIPS ▞

Preserving the tone, facial expressions, music, background noise, all while perfectly syncing the lips.

ElevenLabs

Sounds +27.8% more like you

ElevenLabs: +270% more background-sound error; the laughter, the music, the ambience

Makes 54.7% fewer translation errors; changes or loses important ideas

Delivered up to 4K, true 5.1 surround or stereo mix.

Read the full study →
YouTube

Sounds +182.9% more like you

YouTube: +232.6% more background-sound error

Makes 70.3% fewer translation errors; changes or loses important ideas

Delivered up to 4K, true 5.1 surround or stereo mix.

Read the full study →
Human

100.3% of expert human translation quality

Delivered up to 4K, true 5.1 surround or stereo mix.

Read the full study →
ElevenLabsElevenLabsElevenLabs

ELEVENLABS · THEIR DOCS, READ OCTOBER 30, 2026

Editing the translation means their old model.

On ElevenLabs' current Dubbing v2, in alpha, editing the translation and regenerating the audio through the API is for their Enterprise plans only. Their full editor, Dubbing Studio, is "only available via the v1 model" and "in maintenance mode", in their words. Dubbing v1 is the model our 418-pair study measured, and its output is mono.

Read the full study →
++
Familiar closer to the real speaker, all 11 languages+27.8%
ElevenLabs more background error: the music, the ambience261%
Familiar on laughter and reaction shape+243.7%

ElevenLabs Dubbing v1 · 418 paired outputs · 11 languages · August 5, 2026

Their docs ↗