12-second example · multi_area
Remove promotional text from a UGC product video
Watch two-region text removal in a 12-second product demo: an upper label and changing lower copy. Includes the real multi_area API result, rectangles and measured charge.
multi_area- Clip length
- 12 s
- Source size
- 1280 × 720
- Recorded API charge
- $0.090
- Processing
- 102.0 s
Measured 2026-10-06. USD API charge for 12 billable seconds; web points are separate. 132.9 seconds from submission to completion, including validation and queue time. This is a recorded run, not a latency guarantee.
When to use this workflow
Clear old campaign copy from authorized product footage before creating a new ad or language version.
Why this removal mode?
Two non-overlapping rectangles target the upper label and lower copy while leaving the central face outside the selected regions. multi_area uses the full-frame billing rate.
Result review
The upper label and changing lower copy are removed in the reviewed frames. The face and moving product remain visible; the lower clothing area becomes smoother at some moments.
What this example cannot prove
Hands and the product move near the lower region. Check product contours and clothing texture before using cleaned footage in an advertisement.
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": "multi_area",
"rect": [
{
"x1": 40,
"y1": 26,
"x2": 460,
"y2": 112
},
{
"x1": 280,
"y1": 598,
"x2": 1000,
"y2": 704
}
]
}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
Demonstration promotional text was added to licensed footage. The performer is not endorsing UnmarkAI. The after video is the actual API result, without manual cleanup.
Footage by Tima Miroshnichenko 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.