Multimodal Translation.

Dubbing is finally good.

Reach audiences in 30 languages.

Talk with the teamSee the languages →

Familiar's proprietary diffusion omni-model.

  • Loud music
  • Crowd noise
  • Laughter
  • Multiple people and faces
  • Hands and microphones in front of faces
  • Up to 4K
  • True 5.1 surround or stereo

Movies & TV, Broadcasts, Corporate & Education, Ads

▚ WHO IT'S FOR ▞

  • Film, TV, and microdramas

    The original content distributed to new markets.

  • Creators and podcasts

    Same personalities, in new languages.

  • Brands and agencies

    Existing video, multilingual campaigns.

  • Education and training

    Existing courses, international learners.

  • Platforms

    Dub user videos via the Familiar API.

▚ LANGUAGES ▞

99 languages in. 30 languages out.

Send footage in any of the 99; the dub comes back in any of the 30, in the same actor's voice and lips.

DUBBED INTO30

  • Arabic
  • Belarusian
  • Bulgarian
  • Cantonese
  • Catalan
  • Croatian
  • Danish
  • Dutch
  • English
  • French
  • German
  • Greek
  • Indonesian
  • Italian
  • Japanese
  • Kazakh
  • Korean
  • Latvian
  • Lithuanian
  • Mandarin
  • Norwegian
  • Portuguese
  • Russian
  • Serbian
  • Slovak
  • Spanish
  • Swedish
  • Thai
  • Ukrainian
  • Vietnamese

UNDERSTOOD FROM99

  • Afrikaans
  • Amharic
  • Arabic
  • Armenian
  • Assamese
  • Asturian
  • Azerbaijani
  • Bangla
  • Belarusian
  • Bosnian
  • Bulgarian
  • Burmese
  • Cantonese
  • Catalan
  • Cebuano
  • Croatian
  • Czech
  • Danish
  • Dutch
  • English
  • Estonian
  • Filipino
  • Finnish
  • French
  • Fula
  • Galician
  • Ganda
  • Georgian
  • German
  • Greek
  • Gujarati
  • Hausa
  • Hebrew
  • Hindi
  • Hungarian
  • Icelandic
  • Igbo
  • Indonesian
  • Irish
  • Italian
  • Japanese
  • Javanese
  • Kabuverdianu
  • Kannada
  • Kazakh
  • Khmer
  • Korean
  • Kurdish
  • Kyrgyz
  • Lao
  • Latvian
  • Lingala
  • Lithuanian
  • Luo
  • Luxembourgish
  • Macedonian
  • Malay
  • Malayalam
  • Maltese
  • Mandarin
  • Māori
  • Marathi
  • Mongolian
  • Nepali
  • Northern Sotho
  • Norwegian
  • Nyanja
  • Occitan
  • Odia
  • Pashto
  • Persian
  • Polish
  • Portuguese
  • Punjabi
  • Romanian
  • Russian
  • Serbian
  • Shona
  • Sindhi
  • Slovak
  • Slovenian
  • Somali
  • Spanish
  • Swahili
  • Swedish
  • Tajik
  • Tamil
  • Telugu
  • Thai
  • Turkish
  • Ukrainian
  • Umbundu
  • Urdu
  • Uzbek
  • Vietnamese
  • Welsh
  • Wolof
  • Xhosa
  • Zulu

THE HUMAN DUBBING LIMIT

Audiences lose interest when poor voice dubbing on top of a face that doesn't match.

  • Loss of performanceAnother actor's voice on your actor's face with mismatched lips disconnects audiences immediately.
  • Hard to scaleYou can't easily find human voice actors, directors, and studios to cover 30 languages.
  • ExpensiveFull human dubbing, translation plus voice, runs $70 to $150 per finished minute.
  • Current AI falls shortChaining separate models for voice and visual: lips drift, emotion mismatches, background audio distorts.

▚ THE API ▞

Your platform, in every language.

++
Monarch pixel butterfly

The same engine behind your product: every video and livestream your users post, dubbed into your audience's languages, voice + lip-sync in one model, inside your app.

Explore the docs
01POST /v1/dubs

One request per dub

Up to 29 target languages per request; a webhook fires as each dub lands.

02LIVE · EXPERIMENTAL

Live, seconds behindCOMING SOON

Livestreams dub with everyone on camera in their own voice; each language's feed pushes to its own channel.

03/v1/dont-translate

Per-creator control

Do Not Translate lists and a one-line context brief, set per creator, stream, or video, from your UI.

04translate_metadata

Titles & descriptions too

Each language's dub arrives with its title and description translated; links, @handles, and promo codes stay as written.

review=manual

Creative directors review before it goes out.

Lines that can land more than one way, a joke or a jab, come back as three translations with different intent and emotion. Your creative directors pick one, edit any line against the original, and trigger the render; credits only spend then. Teams that trust the flow skip the stop.

KO → EN · seg_12Joke
KO사과하려고 사과 사 왔어.
  1. 1Apples. I'm sorry, right down to the core.Pun kept · sheepish
  2. 2I came to say sorry. I brought apples.Meaning · sincere
  3. 3An apple a day keeps the silent treatment away.New joke · playful
Creative director's pickEDITED
ZH → EN · seg_41Reads three ways
ZH你可真行啊。
  1. 1Wow. You're incredible.Sincere · warm
  2. 2Well, aren't you something.Sarcastic · dry
  3. 3Look at you, hotshot.Teasing · playful
Creative director's pick
POST/v1/dubs/dub_31xk9m/render
POST /v1/live/sessionsCOMING SOON

Broadcasts

Send the broadcast over WebRTC or RTMP; the dubbed output holds a steady beat behind the original while the translation looks ahead. Broadcasts skip the review stop.

YOUR BROADCAST↓ WHIP · RTMP · SRT INFAMILIAR · DUBBED FEEDS↓ WHEP · RTMP · SRT OUTenzhkojaes×29ONE FEED PER LANGUAGE
Explore the docsGet API access

API access is enterprise-only: private integrations under a Studio contract, with volume pricing and 24/7 dedicated support.

▚ BACKED BY ▞

  • Samsung

    Visual Display Business: No. 1 in global TV sales for 20 consecutive years.

  • RedBird Capital Partners

    Paramount, Warner Brothers, DC Studios, and more.

  • Gold House

    KPop Demon Hunters, Avengers Doomsday, Squid Game, and more.

From the world's top universities in audio-visual human research.

  • Stanford
  • Yonsei
  • HKUST
  • University of Waterloo
▚ FAQ ▞

Questions?

We're the first to do voice + lip-sync dubbing in one model; stitching ElevenLabs and HeyGen together still sounds and looks like a stranger. And it's more than AI lip sync: the whole face performs the new language.

In our published benchmark:

  • their newest product had 270% more background sound error: the laughter, the music, the ambience
  • 54.7% fewer important translation errors than their newest product
  • our voice sounded 27.8% more like the real speaker on their Dubbing v1, closer in all 11 languages

On the same clips, ElevenLabs:

  • dropped or invented words 45 times
  • broke laughs and sound effects 8 times
  • lost the speaker's voice 6 times
  • collided overlapping speakers 6 times
  • flattened the delivery 4 times
  • stripped the scene ambience 4 times
  • refuses clips under 11 seconds (the API)

Stitching it yourself runs $11 a minute: $8 for Sync.so lip-sync plus $3 for ElevenLabs audio. Familiar renders voice, lip-sync, and translation in one pass, up to 4K with a true 5.1 surround or stereo mix.

We tested our production pipeline against professional translators, scored blind against expert reference edits: averaged across French, Chinese, Hindi, and Indonesian, our translations scored 100.3% of the first pass professional's quality. A match. One render includes the translation, the speaker's own voice, the scene audio, and the lip-sync, up to 4K with a true 5.1 or stereo mix.

Dubs come out in 30 languages, any to any, in three quality tiers (best first). Footage can come in from 99 source languages.

Tier 1: Cantonese, English, French, German, Indonesian, Italian, Japanese, Korean, Mandarin, Portuguese, Russian, Spanish, Thai, Vietnamese.

Tier 2: Bulgarian, Catalan, Croatian, Dutch, Greek, Lithuanian, Norwegian, Slovak, Swedish.

Tier 3: Arabic, Belarusian, Danish, Kazakh, Latvian, Serbian, Ukrainian.

Each language arrives as a finished video, up to 4K, with the full audio mix as true 5.1 surround or stereo, your pick, in 24-bit PCM WAV. You also get subtitles in .srt and .vtt from the reviewed transcript, the translated title and description, and the audio by itself: the full mix, or the voice alone for your own mix.
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.
Plans are by Studio contract, sized to your catalog: book a call with us. Every dub is delivered up to 4K with a true 5.1 surround or stereo mix; for reference, full human dubbing, translation plus voice, runs $70 to $150 per finished minute.

See your own video in a new language.

Talk with the team