Dubbing v2 is now available via ElevenAPI
The model conditions dubbing on original performances to preserve tone, emotion, and delivery across more than 90 languages.
- Dubbing v2 improves regional accent accuracy, distinguishing variants such as Castilian and Latin American Spanish.
- The model handles background audio, music, sound effects, and multi-speaker scenes.
- A single API call runs translation, voice cloning, dubbing, and synchronization automatically.
- Enterprises can supply custom source transcripts and translations, then regenerate only edited segments.
Developers can now programmatically integrate automated, sync-aware dubbing with voice preservation into their own applications.

Sources
Read this as text
Back to the AI news