Introducing Dubbing v2

Today we’re launching Dubbing v2, our revolutionary new AI dubbing model.

For the first time, the emotion and performance of the original speaker carries across every language. Instead of generating flat, disconnected audio from a transcript alone, Dubbing v2 conditions directly on the original performance - preserving tone, pacing, delivery, and emotional intent.

This solves one of the biggest unsolved problems in AI dubbing: making translated speech feel like the original person actually said it.

Preserving the original performance across 90+ languages

Traditional AI dubbing systems rely heavily on transcripts. While this can produce accurate translations, the resulting audio often loses the nuances that make human speech feel natural. Emotion, timing, emphasis, hesitation, and energy are difficult to reconstruct from text alone.

Dubbing v2 approaches the problem differently. By conditioning directly on the original performance, the model captures the speaker’s intonation and tone and transfers it across languages. The result is dubbing that sounds significantly more natural and expressive, while staying faithful to the original delivery.

Built for natural multilingual delivery

Good dubbing is more than direct translation. Different languages require different phrasing, rhythm, and sentence structure to sound natural. Dubbing v2 adapts translations for spoken delivery while keeping synchronization with the original content. Its sync-aware translation system aligns starts, stops, and pacing automatically, reducing the need for manual adjustment and making the final output feel closer to professionally produced dubbing.

Making high-quality dubbing accessible

Professional dubbing can cost hundreds of dollars per minute and often requires large production pipelines involving translators, voice actors, editors, and audio engineers.

Dubbing v2 automates the process. Creators and businesses can now produce high-quality multilingual content without building complex workflows or coordinating multiple vendors.

For creators: reach global audiences with natural-sounding video

For creators, Dubbing v2 makes it possible to localize YouTube videos and other content with one click inside ElevenCreative. Videos can now sound natural to audiences across languages while preserving the personality and delivery of the original creator. This makes global distribution significantly faster and more accessible without sacrificing quality.

Alongside this release we are launching the Creator Dubbing Partner Program. Eligible creators will get discounted access to Dubbing v2. Apply here.

For marketers: localize campaigns at scale

For marketing teams, Dubbing v2 enables high-quality localization across international markets without rebuilding campaigns from scratch. Ads, product videos, and brand content can now maintain the same emotional impact and delivery style across languages. ElevenCreative powers the full localization workflow end-to-end, helping teams scale multilingual campaigns more efficiently.

For studios and broadcasters: professional dubbing workflows

For studios, broadcasters, and enterprise productions, ElevenProductions combines Dubbing v2 with professional localization services. This includes human translators, expert voice casting, and professional audio mixing, while Dubbing v2 handles the underlying speech generation and synchronization.

The result is a scalable workflow for professional-grade multilingual productions. Learn more.

Get started for free

Dubbing v2 is available today in ElevenCreative and through ElevenProductions. For the next 7 days, you can get started for free with 1 minute of free usage on our Free plan, 15 minutes on our Starter plan and 30 minutes on Creator+ plans.

API access is coming soon, reach out to Contact Sales to learn more.