Flat-pack furniture assembly video: real footage, trimmed steps
Film each assembly step once, trim it for $0.02, caption it with exact cues for $0.20. Add a wall-anchor step, since CPSC cites 199 child tip-over deaths.

For an assembly video, film a person doing each step with the real parts, cut each step out of the raw take with video trim, then burn the step number and one instruction onto it with authored caption cues. Real footage matters here: a generated clip can show a screw going where none goes. Stored guidance on 3D-render assembly clips exists in the 3D render post, but for the instructions your customer will actually follow, use the real build.
Cost on Sume, from the docs read 2026-10-03: trim is $0.02 per job and captions are $0.20 per job for clips up to 60 seconds.
Cost for a six-step dresser
One trim and one caption job per step, so six clips. The totals are arithmetic on the two rates above.
| Item | Jobs | Rate | Total |
|---|---|---|---|
| Video trim, one per step | 6 | $0.02 | $0.12 |
| Video captions, one per step | 6 | $0.20 | $1.20 |
| Total | 12 | $1.32 |
The steps
Import the raw take to your workspace first. Video trim takes a media.sume.com clip, a start, and exactly one of end or duration, and returns a new MP4 with a new artifact id. Keep precision at its default exact for frame-accurate cuts.
Then video captions with cues. Assembly footage is often silent or has a hammer in the background, and authored cues skip speech-to-text so that does not matter. One action per cue: "Step 3: Slide drawer rails into the side panels until they click."
curl -X POST https://api.sume.com/v1/video-captions \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: dresser-step3-001" \
-d '{
"video_url": "https://media.sume.com/artifacts/example/step3.mp4",
"cues": [
{
"text": "Step 3",
"start": 0.3,
"end": 2.5
},
{
"text": "Slide rails into the side panels until they click",
"start": 2.5,
"end": 9
}
]
}'Make the last step the anchor
On the CPSC page, read 2026-10-03, the agency adopted ASTM F2057-23 as a mandatory standard for clothing storage units, effective September 1, 2023, and says it documented 234 fatalities from clothing storage unit tip-overs from January 2000 through April 2022, including 199 child fatalities. It recommends that consumers anchor furniture, including dressers, securely to the wall.
So end the video with a wall-anchor step on a stud or the fasteners your product's instructions call for. I did not read the standard itself, so follow the manual that ships with your unit for hardware. Sume does not review your instructions for safety; it trims and captions what you filmed.
Sources
Related posts
More in Use cases
- Florist's Thanksgiving centerpiece how-to: 5 captioned clips for $1.70
Five 30-second centerpiece tips from your own phone footage, each trimmed, voiced, rendered and captioned, cost $0.34 each and $1.70 in total on Sume.
- Flyer to video: turn a promo flyer into a vertical clip
Make a 10-second vertical clip from a flyer image and a short clip of the shop, using Timeline 1.0 and a compose overlay for the offer.
- Run 100 ad hook variants in one Sume Format bulk run
Sume Format bulk runs take 1-100 items with concurrency 1-16. What to put in each item, and what bulk runs do not offer: no queue webhook, no cancel-queue call.
- A 40-clip season on each Sume plan: how many rounds of jobs
Eight episodes of five clips is 40 video jobs. Pro runs 4 at a time, Scale 20. Rounds per plan, plus a submitter that survives queue_full.
Written by Sume