Remove burned-in subtitles from your own video
A video with subtitles (or another line of text) burned into its picture in, the same video out with that text painted out: a text detector finds the lines inside region (shares of the frame; default the lower 40 %), an inpainting model fills the background in under them, and every pixel outside the text stays the source's own; the sound is copied untouched, the picture re-encoded once at quality. start / end limit the work to one stretch. The customer's OWN video only; not a watermark remover (a logo or someone else's mark is not removed). Runs on a render node: minutes, not seconds. The render's text_removal reports the band, the frames looked at and painted and the lines found (0 = nothing in the band). Asynchronous: poll GET /v1/executions/{id}.
Billing: Per second of output at the text-removal tier (clean_text: the inpainting's measured compute on a render node); a clip where no text was found in the band pays a plain re-encode (the hd tier) — the estimate assumes text. Failed renders are not charged. · Rate limit: 30/min · Asynchronous
Request
- Base URL: https://apihub.co.il
- URL: https://apihub.co.il/v1/studio/clean-text
- Auth: HTTP bearer
Headers
Replay-safe: the same execution is returned instead of charging twice
Group calls into one job (e.g. one video) — see GET /v1/usage?tag=…
Wait for the job inside this call (ms)
Request body
Response
Completed (or 202 while processing)
Changes
No recorded changes to this operation across all 2 revisions of this API.