elevenlabs/dubbing

Translate audio and video into 90+ languages while preserving each speaker's voice, emotion, and timing

Capabilities

No capability data available

Cost

Community model (estimated from hardware time)

Input Parameters

Name	Type	Description	Default	Constraints
`target_language`*	string	Language to dub the content into, as a BCP-47 tag. Some languages also offer region-qualified dialects (e.g. 'es-MX', 'pt-BR', 'en-GB').	`—`	afaksqamarar-EGhyasazeubebsbgmyyuecacebzhzh-TWhrcsdadgonlenen-AUen-CAen-GBen-USetfilfifrfr-CAfr-FRglkadeelguhahehihuisiditjajvknkkkirwrnkokylvltlgmkmsmlcmnmrmnnenofaplptpt-BRpt-PTparorunsostsdsksleses-ARes-CLes-ESes-MXsuswsssvtgtatethbotstntrukuruguzveviwarcywoyozu
`audio_or_video_file`	string(uri)	Audio or video file to dub. Provide this or source_url.	`—`	—
`cloning_strength`	integer	How strongly the dubbed speakers clone the source voices, from 0 to 10. Higher values prioritize resemblance to the original voice; lower values give the model more freedom for natural delivery in the target language. The default of 7 works well for most content.	`7`	min: 0, max: 10
`source_language`	string	Language of the source media, as a BCP-47 tag. Leave as 'auto' to detect it automatically.	`"auto"`	autoafaksqamarar-EGhyasazeubebsbgmyyuecacebzhzh-TWhrcsdadgonlenen-AUen-CAen-GBen-USetfilfifrfr-CAfr-FRglkadeelguhahehihuisiditjajvknkkkirwrnkokylvltlgmkmsmlcmnmrmnnenofaplptpt-BRpt-PTparorunsostsdsksleses-ARes-CLes-ESes-MXsuswsssvtgtatethbotstntrukuruguzveviwarcywoyozu
`source_url`	string	Public URL of the source audio or video file to dub (e.g. a direct link, YouTube, or TikTok URL). Provide this or audio_or_video_file.	`—`	—

target_languagerequiredstring

Language to dub the content into, as a BCP-47 tag. Some languages also offer region-qualified dialects (e.g. 'es-MX', 'pt-BR', 'en-GB').

afaksqamarar-EGhyasazeubebsbgmyyuecacebzhzh-TWhrcsdadgonlenen-AUen-CAen-GBen-USetfilfifrfr-CAfr-FRglkadeelguhahehihuisiditjajvknkkkirwrnkokylvltlgmkmsmlcmnmrmnnenofaplptpt-BRpt-PTparorunsostsdsksleses-ARes-CLes-ESes-MXsuswsssvtgtatethbotstntrukuruguzveviwarcywoyozu

audio_or_video_filestring

Audio or video file to dub. Provide this or source_url.

cloning_strengthinteger

How strongly the dubbed speakers clone the source voices, from 0 to 10. Higher values prioritize resemblance to the original voice; lower values give the model more freedom for natural delivery in the target language. The default of 7 works well for most content.

Default: 7min: 0, max: 10

source_languagestring

Language of the source media, as a BCP-47 tag. Leave as 'auto' to detect it automatically.

Default: "auto"

autoafaksqamarar-EGhyasazeubebsbgmyyuecacebzhzh-TWhrcsdadgonlenen-AUen-CAen-GBen-USetfilfifrfr-CAfr-FRglkadeelguhahehihuisiditjajvknkkkirwrnkokylvltlgmkmsmlcmnmrmnnenofaplptpt-BRpt-PTparorunsostsdsksleses-ARes-CLes-ESes-MXsuswsssvtgtatethbotstntrukuruguzveviwarcywoyozu

source_urlstring

Public URL of the source audio or video file to dub (e.g. a direct link, YouTube, or TikTok URL). Provide this or audio_or_video_file.

Version: 1ca6320db9b5Updated: 9/20/202620 runs