12-second example · sel_area
Remove two-line word-highlight captions from a tutorial video
A 12-second woodworking clip shows removal of two-line bold captions with a bouncing highlighted word. Watch the synchronized input and real API output with the exact region and charge.
sel_area- Clip length
- 12 s
- Source size
- 1280 × 720
- Recorded API charge
- $0.045
- Processing
- 101.9 s
Measured 2026-10-06. USD API charge for 12 billable seconds; web points are separate. 118.8 seconds from submission to completion, including validation and queue time. This is a recorded run, not a latency guarantee.
When to use this workflow
Replace instructional captions before translating a tutorial or updating its wording.
Why this removal mode?
Two-line Montserrat bold captions stay in the lower band. The currently timed word turns yellow and briefly scales to 116%, matching the product’s bounce mode. A 1192 × 188 pixel selection covers about 24.3% of the frame, below the half-frame limit.
Result review
The two-line words and yellow highlights are no longer readable in the reviewed caption transitions. Sawdust and wood grain in the lower band look softer than the input; the central tool and gloves remain outside the selected region.
What this example cannot prove
Wood grain and sawdust are moving behind the caption band. Reconstruction may soften those details; this clip does not establish performance on every tutorial.
No model version was returned by the public job response. One short clip cannot predict results for other footage. Check the full result at normal speed and around each word change.
Reproduce this API request
Upload your own authorized video first, then replace the upload ID. Coordinates refer to this example’s 1280 × 720 source pixels; recalculate them for a different video.
{
"type": "remove_text",
"input": {
"upload_id": "upl_your_uploaded_video"
},
"mode": "sel_area",
"rect": {
"x1": 44,
"y1": 520,
"x2": 1236,
"y2": 708
}
}Send Authorization: Bearer $UNMARKAI_API_KEY from your server and a stable Idempotency-Key for this request. Never expose the key in browser code.
Source and demonstration method
Two-line demo captions use UnmarkAI’s actual subtitle bounce renderer (Montserrat 800, white text, yellow active word, black outline, 116% peak over 220 ms). Editorial copy and word timings are scripted for demonstration, not the speaker’s words or an ASR transcript. The after video is the actual API result, without manual cleanup.
Footage by Sururi Ballıdağ Director on Pexels, used under the Pexels License. Prepared at 1280 × 720, H.264, 25 fps, with no audio. The comparison places the processed input and downloaded API output on the same timeline; only comparison labels and encoding are added.
Use owned or licensed footage for caption replacement. Keep attribution and required disclosures in content you publish.