Dubbing
Learn how to translate audio and video while preserving the emotion, timing & tone of speakers.
Learn how to translate audio and video while preserving the emotion, timing & tone of speakers.
ElevenLabs dubbing translates audio and video across 90+ languages while preserving the emotion, timing, tone and unique characteristics of each speaker. Our model separates each speaker’s dialogue from the soundtrack, allowing you to recreate the original delivery in another language. It can be used to:
We also offer a fully managed dubbing service for video and podcast creators.
Edit transcripts and translate videos step by step in Dubbing Studio.
Learn how to integrate dubbing into your application.
Cloning strength is the configurable setting in Automatic Dubbing on the Dubbing v2 Alpha model. The default value of 7 works well for most content. Higher values prioritize voice similarity to the original speaker, which can sound less natural across languages with very different phonetic characteristics. A higher setting can also carry over more of the original accent into the dubbed output. Lower values give the model more freedom for natural delivery in the target language at the cost of resemblance to the original voice.
Dubbing v2 does not include a watermark toggle. Free-tier dubs are watermarked automatically; paid-tier dubs are not. There is no watermark-for-credit-discount option on Dubbing v2. The legacy V1 dubbing flow and Dubbing Studio were the only places where the watermark discount existed.
Refer to our pricing page for detailed credit costs.
Supports 90+ languages including English, Spanish, French, German, Japanese, Chinese, Arabic, and more.
too_many_concurrent_requests error and should wait for existing jobs to complete before starting new ones.Realtime or live dubbing is not currently available.
If a Dubbing Studio job fails or you cancel it, the credits are automatically refunded to your account. Dubbing v2 (priced per minute in US dollars on Automatic Dubbing) is not charged for failed jobs. If a dub is stuck in Queued or Loading for an extended period, cancel and resubmit it. You will not lose credits by doing so.
The Dubbing v2 API is not yet live but is expected to launch in the coming weeks.
Automatic Dubbing on the main Dubbing page uses Dubbing v2 by default. To use the legacy V1 dubbing model and the original dubbing dialog, click Advanced and then Use Legacy V1 Dubbing Model. The legacy dialog includes the V1 watermark-for-credit-discount option and is the only way to reach Dubbing Studio from this page.