Skip to main content
POST
Create Spot Transcription
Transcription drifts on a noisy passage, a crosstalk section, or a stretch in another language. Rather than re-running the whole job, name the run and the window in seconds and only that span is transcribed again. Give source_language when the window is in a different language from the rest of the run, or set auto_detect_language to have it detected. Omit both and the run’s own source language is used. Omit start_seconds and end_seconds to re-transcribe the whole run. Track progress by polling /spot-transcription/{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 re-transcribe. Must already have a transcript.

revision_num
integer | null

Revision to re-transcribe. Defaults to the run's latest revision.

Required range: x > 0
start_seconds
number | null

Start of the window to re-transcribe. Defaults to the start of the media.

Required range: x >= 0
end_seconds
number | null

End of the window to re-transcribe. Defaults to the end of the media.

Required range: x > 0
source_language
integer | null

Language spoken in the window. Defaults to the run's source language.

auto_detect_language
boolean
default:false

Detect the spoken language instead of supplying source_language.

Response

Successful Response

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