Dubbing v2 is now available via ElevenAPI

Developers can now embed AI dubbing directly into their products and workflows.

Dubbing v2 fixes flat audio by conditioning directly on the original performance. It ensures that tone, emotion, and delivery are preserved across 90+ languages. 

Sync-aware translation logic means that starts and stops align with the original out of the box.

New model improvements

Dubbing v2 now captures regional accents with sharper locale accuracy, distinguishing variants like Castilian and Latin American Spanish. It also handles background audio, music, and effects better, including scenes with multiple speakers.

Handle the full pipeline through a single API

Translation, voice cloning, dubbing, and sync all run automatically. For more granular editing, enterprises can go further: bring your own source transcript and target language translations, or edit the ones the model produces, then regenerate only the segments you change.

Getting started

Read the ElevenAPI dubbing quickstart guide and start building.