Skip to main content
POST
Create Scene Audio Description
Audio description makes a video usable without sight: the action between the dialogue is described aloud. Point this at a run that already has a transcript. Name the voice to narrate with โ€” either a speaker_id from the run or a voice_id from your library โ€” or omit both and let the pipeline choose. Track progress by polling /scene-audio-description/{task_id} with the task_id returned in the response.

Authorizations

x-api-key
string
header
required

The x-api-key is a custom header required for authenticating requests to our API. Include this header in your request with the appropriate API key value to securely access our endpoints. You can find your API key(s) in the 'API' section of our studio website.

Headers

traceparent
string | null

Body

application/json
run_id
integer
required

The run to describe. Must already have a transcript.

revision_num
integer | null

Revision to describe. Defaults to the run's latest revision.

Required range: x > 0
speaker_id
integer | null

Speaker whose voice narrates. Omit both to let the pipeline choose.

Required range: x > 0
voice_id
integer | null

Voice that narrates the description.

Required range: x > 0

Response

Successful Response

task_id
string | null
required
Last modified on October 22, 2026