All articles
Languages·Jun 18, 2026· 5 min read

How we add new languages without breaking dubbing quality

Every new language gets the same voice tuning pass. Here's the multi-stage evaluation we run before shipping a new language.

By Languages Team

We added six languages last quarter: Bengali, Tamil, Telugu, Marathi, Gujarati, and Kannada. They went live together. Nothing regressed. Here's the boring, careful process that makes that possible.

Stage 1 — Voice fit, not just accuracy

We don't measure language coverage by BLEU score. We measure it by listening. Our first filter is a 30-second clip of conversational audio per language, dubbed by the candidate voice. If it sounds wrong (wrong gender, wrong register, or a tell-tale synthetic artifact) we drop the candidate voice and try the next one.

Stage 2 — Idiom coverage

Each language has a list of common idioms. We feed 30 of them into a private evaluation set, check the dubbed output, and reject the candidate if more than 10% feel off.

Stage 3 — Long-tail regression

After passing Stage 2, we hold the language in shadow mode for one week: real users hit the model but the outputs aren't surfaced. We log the latency, the artifact rate, and the user corrections. Only then do we promote it.

"Languages aren't features you ship. They're features you grow into."

Try it yourself

Translate any video in real time.

Side-load the SyncDub extension in two minutes. 100 minutes of dubbing — yours forever.

Download extension