Better than Humans. Performances, Preserved.

Dubbing is finally good.

Talk with the teamSee the full benchmark →

Movies & TV, Broadcasts, Ads -- in every language

Localization & MCNs
Movies & TV
Content Distributors & Platforms
Broadcasts

▚ WHAT YOU GET ▞

The whole translation, delivered.

Voice

Your own voice speaks the new language; tone, emotion, and delivery intact.

Lip-sync

The whole face performs the new language: eyes, brow, cheeks, head.

Subtitles

Free .srt and .vtt with every dub, built from the transcript you reviewed.

Broadcasts

Streams and broadcasts dubbed as they air, everyone on camera in their own voice.

▚ LIVE ▞

Broadcasts, dubbed as they air.

Broadcast dubs run 5 to 9 seconds behind the original over SRT or RTMP: translation 2 to 6 seconds depending on the quality setting, voice about 1 second, lip-sync about 2 more. Everyone on camera is dubbed in their own voice; music passes through.

END-TO-END LATENCY
SRT · RTMP · WEBRTC
TRANSLATION
2–6 s
VOICE
~1 s
+ LIP-SYNC
~2 s
END TO END
5–9 s
LIVE FROM 11 LANGUAGESENESDEFRPTITNLVIARJAZHinto all 29 others· uploads dub from all 30
Book a meeting

▚ THE API ▞

Your platform, in every language.

++
Monarch pixel butterfly

The same engine behind your own product: every video and livestream your users post, dubbed into the languages your audience watches, voice + lip-sync in one model, without anyone leaving your app.

Explore the docs
01POST /v1/dubs

One request per dub

Send one request with up to 29 target languages; a webhook fires as each finished dub lands.

02LIVE · WEBRTC + RTMP

Live, seconds behind

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, per stream, or per video, from your own UI.

04translate_metadata

Titles & descriptions too

Send the video's title and description and each language's dub arrives with its own translated pair; links, @handles, and promo codes stay exactly as written.

review=manual

Review before it goes out

With review on, a dub pauses after translation: your team checks every line against the original, edits what it wants, and triggers the render; credits only spend then. Teams that trust the flow skip the stop entirely.

TRANSCRIPT · dub_31xk9min_review
ENToday we're testing the new build.
ESHoy probamos la nueva versión. EDITED
POST/v1/dubs/dub_31xk9m/render
POST /v1/live/sessions

Broadcasts

Open a session and send the broadcast over WebRTC or RTMP; the dubbed output holds a steady beat behind the original while the translation looks ahead. Review is an async-only stop; broadcasts flow straight through.

YOUR BROADCAST↓ WHIP · RTMP · SRT INFAMILIAR · DUBS IN REAL TIME↓ WHEP · RTMP · SRT OUTesptjakozh×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.

▚ BRAND SAFETY ▞

Control at every step.

Review before release

Every dub waits for your approval: your team checks the translation line by line, edits it, then triggers the render.

Rights, on the record

Nothing renders without an explicit rights confirmation, recorded on the job.

Identity, protected

Your voice and face stay yours. We translate people, never fabricate them.

A direct line

Studio contracts run with a named point of contact: default limits raised on request, live sessions provisioned with an engineer on the line.

FAMILIAR RESEARCHWHAT MATTERS IN VIDEO TRANSLATION

Translation, voice, on-screen text, lip-sync: every part of dubbing is one problem, understanding the video and generating it back.

What matters in video translation →
Natural translationA new script in the target language; not a sentence-for-sentence mapping.
Natural audioThe same person, same emotion, same emphasis, in the new language.
On-screen textAdapted for the moment it appears in, without damaging the video.
Lip-syncInvisible. The viewer never notices it happened.

▚ BACKED BY ▞

YCombinator

Familiar is in the Summer 2026 batch of the accelerator behind Airbnb, Stripe, Whatnot, and DoorDash.

Familiar on Y Combinator

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, two tools and two bills. Familiar renders voice, lip-sync, and translation in one pass.

We tested our production pipeline against expert 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. The price is not: professional translation alone runs $22 to $45 per spoken minute, and full human dubbing, translation plus voice, $70 to $150 per finished minute.

30 languages, any to any, in three quality tiers (best first).

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 with the full audio mix. 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. For reference, full human dubbing, translation plus voice, runs $70 to $150 per finished minute.
▚ STILL CURIOUS? ▞Talk with the team