PREVIEW · CLOSED ACCESSAPI keys are issued under Studio contracts. Email the team
API REFERENCE · PLATFORM
Private inference
Every dub is processed on Familiar's own eight-figure cluster of NVIDIA B300 GPUs in Toronto, Canada. Your media is never processed on a public cloud like Google Cloud or AWS, and never by a third-party inference provider, so it is never leaked.
Where your media is processed
The models that translate, voice and lip-sync your footage run on compute Familiar owns and operates: an eight-figure cluster of NVIDIA B300 GPUs, the best on the market, in Toronto, Canada. There is no public cloud and no third-party inference provider in the path of a dub; the processing stays on compute we own.
| FACT | VALUE |
|---|---|
| GPUs | NVIDIA B300, the best on the market |
| Cluster | Eight figures, USD |
| Location | Toronto, Canada |
| Operator | Familiar Labs, on compute we own |
| Public cloud in the processing path | None (no Google Cloud, no AWS) |
| Third-party inference provider | None |
The path of a dub
- Your footage comes in through the API or the console (Create a dub).
- Translation, review and the render are processed on the Toronto cluster.
- The finished files come back to you as described in Outputs & subtitles.
The website, the console and the data they keep about your account are described in the privacy policy, which names every processor.