POST
/
v1
/
dubbing
curl --request POST \
  --url https://api.elevenlabs.io/v1/dubbing \
  --header 'Content-Type: multipart/form-data' \
  --form 'name=<string>' \
  --form 'source_url=<string>' \
  --form source_lang=auto \
  --form 'target_lang=<string>' \
  --form num_speakers=0 \
  --form watermark=false \
  --form start_time=123 \
  --form end_time=123 \
  --form highest_resolution=false
{
  "dubbing_id": "<string>",
  "expected_duration_sec": 123
}

On the 8th of May 2024 we launched the Dubbing API for all ElevenLabs tiers

​
Creating dubs using our API

In order to create dubs using our API be sure to set mode="automatic", and upload your file to be dubbed using the file parameter. At this time automated dubbing doesn’t support automatically dubbing from a csv_file/foreground_file/background_file.

Headers

​
xi-api-key
string

Your API key. This is required by most endpoints to access our API programatically. You can view your xi-api-key using the 'Profile' tab on the website.

Body

multipart/form-data
​
file
file

A list of file paths to audio recordings intended for voice cloning

​
name
string

Name of the dubbing project.

​
source_url
string

URL of the source video/audio file.

​
source_lang
string
default:auto

Source language.

​
target_lang
string

The Target language to dub the content into.

​
num_speakers
integer
default:0

Number of speakers to use for the dubbing. Set to 0 to automatically detect the number of speakers

​
watermark
boolean
default:false

Whether to apply watermark to the output video.

​
start_time
integer

Start time of the source video/audio file.

​
end_time
integer

End time of the source video/audio file.

​
highest_resolution
boolean
default:false

Whether to use the highest resolution available.

Response

200
application/json
Successful Response
​
dubbing_id
string
required
​
expected_duration_sec
number
required