12-second example · all_area
Remove two-line highlighted captions from a vertical creator video
A 12-second vertical clip demonstrates full-frame removal of two-line captions with a bouncing highlighted word, first below and then above the speaker. Includes the actual API result and charge.
all_area- Clip length
- 12 s
- Source size
- 720 × 1280
- Recorded API charge
- $0.090
- Processing
- 170.3 s
Measured 2026-10-06. USD API charge for 12 billable seconds; web points are separate. 202.1 seconds from submission to completion, including validation and queue time. This is a recorded run, not a latency guarantee.
When to use this workflow
Create a clean master of authorized vertical footage for new captions on Reels, TikTok or Shorts.
Why this removal mode?
Two-line captions use the product’s Montserrat bold bounce mode: the currently timed word highlights yellow and scales to 116% before settling. The caption block changes from the lower band to the upper band after eight seconds, so this example uses all_area without a rectangle.
Result review
The lower two-line captions and upper caption block are removed across the reviewed pages. Glasses, hair and the laptop remain visible; skirt folds and wall texture inside reconstructed areas can soften.
What this example cannot prove
Full-frame detection may also affect text you want to keep. Review the face, glasses, laptop and background; use a selected region when only one band needs cleanup.
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 720 × 1280 source pixels; recalculate them for a different video.
{
"type": "remove_text",
"input": {
"upload_id": "upl_your_uploaded_video"
},
"mode": "all_area",
"rect": null
}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 ANTONI SHKRABA production on Pexels, used under the Pexels License. Prepared at 720 × 1280, 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.