ABSTRACT
The test
of expert human translation quality
FRENCH, CHINESE, HINDI, INDONESIAN · FIRST PASS FOR EXPERT PROFESSIONAL TRANSLATORSone Familiar render: the translation, the speaker's own voice, the scene audio, and the lip-sync, delivered up to 4K with a true 5.1 or stereo mix
TRANSLATION ALONE IS WHAT THE PROFESSIONAL RATE BUYSEach source segment was translated twice, once by Familiar and once by a professional human translator; both versions were judged blind against expert reference edits.
Results by language
| Language | Relative score | 95% range |
|---|---|---|
| French | 100.0% | 97.0–105.4 |
| Chinese | 98.2% | 95.6–100.0 |
| Hindi | 103.3% | 100.4–108.5 |
| Indonesian | 99.6% | 97.6–103.2 |
| Average | 100.3% | – |
Read the ranges, not the decimals: a range that spans 100 is a statistical tie with the professional.
The whole job, at published prices
Full human dubbing, translation plus voice, runs $70 to $150 per finished minute, so it isn't usable for most of the world: even top productions dub only a few languages because of the cost, the people and the time, and smaller productions, shows and vertical dramas don't dub at all. Translation at published per-word rates ($0.15 to $0.30 per word) is only the first line item; the published rate cards for the rest:
| Option | Per finished minute | For 60 minutes |
|---|---|---|
| Published human translation + review | $10 median $11.95 mean | $600 median $717 mean |
| Published human dubbing packages (voice, direction, mix) | $39–$94 ~$60 midpoint | $2,340–$5,640 ~$3,600 midpoint |
| Full human dubbing, translation plus voice | $70–$150 | $4,200–$9,000 |
| Premium studio dubbing | From $128 | From $7,680 |
SOURCES & MATH
- $10 median / $11.95 mean: 11 target languages, Netflix's published rate card.
- $39–$94 packages: Voquent; from $128: Gotham Lab (references below).
- Full human dubbing = translation plus voice.
- Published prices, not identical workflows; rates vary by language, talent, studio, revisions, and volume.
The same translation, inside a finished dub
This study scores translation text alone; the full head-to-head on finished dubs from Familiar is Familiar vs ElevenLabs Dubbing: Two Paired Studies.
fewer important translation errors than ElevenLabs' newest Dubbing v2 (Alpha)
29 VS 64 · 111 PAIRED DUBS · MANDARIN, SPANISH, JAPANESE
ElevenLabsElevenLabsTHEIR DOCS, READ OCTOBER 30, 2026Editing the translation means their old model.
+27.8%
FAMILIAR CLOSER TO THE REAL SPEAKER · ALL 11 LANGUAGES
261%
ELEVENLABS MORE BACKGROUND ERROR · THE MUSIC, THE AMBIENCE
+243.7%
FAMILIAR ON LAUGHTER AND REACTION SHAPE
Where professionals come in
A professional brings what no metric captures: transcreation of wordplay, legal and brand review, accountability for a single high-stakes document. For spoken video at catalogue scale, human dubbing isn't usable: even top productions dub only a few languages because of the cost, the people and the time.
To test the translation on your own footage: How to Run an AI Dubbing Pilot (2026).
REFERENCES
- [1]Familiar vs ElevenLabs benchmark: full results, intervals, and listening examples
- [2]WMT24++ dataset: the professional translations and expert reference edits
- [3]WMT24++: Expanding the Language Coverage of WMT24 to 55 Languages & Dialects (paper)
- [4]Netflix Post Production: published translation rate card
- [5]Voquent: how much does dubbing cost?
- [6]Gotham Lab: dubbing services (premium studio rates)
- [7]ATA 2025 Compensation Survey (interpreter rates)
- [8]Smartling: Translation rates -- how much does translation cost?
- [9]Tomedes: Translation rates and why translation prices vary
Multimodal Translation
Familiar Labs builds generationally better dubbing with a Multimodal Localization Decision Model (MLDM), the first foundation model for multimodal translation: one model decides what to localize across text, audio and visual, and shows you the choices. Your voice and lips, carried into new languages. They're a team of 7 with PhDs, backed by Samsung, RedBird, Gold House. Our mission