Optionalargs: { client?: Client; key?: string }Optionaloptions: Options<AvatarsData, ThrowOnError>Dub audio or video
Generate dubbed video or audio. A composited lip sync can also be added for video dubbing.
Generate avatar video from text
Generates an avatar video from a provided transcript or audio file. You can provide the transcript either as plain text or a pre-signed URL. The API is asynchronous, so the response will include a job ID and a status URL for tracking the running job.
Reframe video
This endpoint enables you to reframe video using AI. Provide video input with a pre-signed URL to generate reframed video output.
This API has more limited capabilities than the v2 endpoint, and may be deprecated soon. It's recommended to use the v2 endpoint instead.
Reframe video v2
This endpoint enables you to reframe the input media. You can provide a video input via a pre-signed URL to generate reframed output video.
Generate speech from text
This endpoint generates speech from a transcript. You can provide the transcript either as plain text or a pre-signed URL. The response will include a job ID and a status URL for tracking the job.
Fetch video rendering presets
Returns a list of predefined social-first encoding presets for rendering outputs.
Optionaloptions: Options<GetPresetsData, ThrowOnError>Get job result
This endpoint retrieves the result of an asynchronous reframed job initiated using the job ID.
Get job status
Provides the status and result of an asynchronous job. For Dynamic Graphics Render (DGR), returns the status of a Describe template or Render job.
Describe template
Analyzes a MOGRT (video template) file and returns a manifest of editable controls; fonts, images, audio, video and other supported values.
Render template
Renders one or more video variations by applying overrides and export presets. Submit up to 10 overrides per call for a subset of editable layers and get a pre-signed URL link to download the video file. For layers that are not editable, the system defaults are automatically applied at export.
Transcribe media
Generates transcripts and captions for the input audio or video in the source language or in a target language.
Get available voices
This endpoint provides the list of all available voices for the user's enterprise.
Optionaloptions: Options<VoicesData, ThrowOnError>
Get available avatars
Retrieves the list of all available avatars for the user's enterprise.