Translate Video

Translates a video into one or more of 175+ supported languages with natural-sounding voice and accurate lip-sync.

Body Params
string
required

URL of the video file to be translated. Supports direct video file URLs, Google Drive URLs, and YouTube URLs.

string

Title of the video.

string
required

The target language in which the video will be translated. Either output_language or output_languages must be provided. Omitting both or defining both will result in an error.

output_languages
array of strings
required

List of multiple target languages to translate the same video in a single request. Enables faster batch processing. Either output_language or output_languages must be provided. Omitting both or defining both will result in an error.

output_languages*
boolean
Defaults to false

Translate only the audio, ignore the faces and only translate the voice track in this video. Ideal for videos where the speaker is not visible, such as narrations, voiceovers, etc.

int32

Number of speakers in the video.

string

Custom ID for callback purposes. Returned in the status/webhook payload for tracking.

string

Stretch or shrink portions of your video to enhance conversational fluidity and translation quality between languages with different speaking rates.

string

Unique identifier of the Brand Glossary. It is used to apply predefined translation and pronunciation rules such as translation exclusions, enforced terms, vocabulary mappings, and tone preferences. Can be retrieved from List Brand Voices endpoint.

string

URL to notify when video rendering is complete, useful when your callback endpoint is dynamic and each video requires a separate callback. Using a webhook endpoint is still the recommended approach, as it provides more customization options such as secrets, event filtering, and more. If both webhook and callback_url are used, events will be sent to both endpoints.

boolean
Defaults to false

Set to true to ensure the input quality matches the output quality.

string
Defaults to fast

Specify the mode for video translation quality. Default mode is fast for faster generation, ideal for standard translations and videos with limited facial movement. Choosing quality mode will ensure highly natural lip-sync with a context-aware model, but will cost 2x more credits.

Response

Language
Credentials
Header
Response
Click Try It! to start a request and see the response here! Or choose an example:
application/json