Remove the card behind burned-in captions: colors.card null
Set design.colors.card to null on a Sume caption job to show no card. It works on styles that support design, not on punch or tiktok-green.

To remove the card behind burned-in caption words, send design.colors.card as null in the Sume caption request. The video captions page lists card among the colors fields and notes that null shows no card. It applies only to styles that read design tokens: punch and tiktok-green do not support design at all, because they render on a path that reads none of the tokens.
The request
Pick a style that supports design, such as weight-shift or pill-karaoke, and override one token. Sume merges each field over the style's own value, so one key changes one thing.
{
"video_url": "https://example.com/clean.mp4",
"style": "pill-karaoke",
"design": { "colors": { "card": null } }
}Which styles it helps
The docs do not promise that every style draws a card, so test one short clip before a batch. A style with no card has nothing for null to remove.
| Style | Accepts design | Note |
|---|---|---|
| slam | Yes | Latin default. |
| black-outline | Yes | White fill on a thick black outline. |
| weight-shift, highlight, clip-wipe, editorial-emphasis | Yes | Phrase cards or blocks, per the style. |
| pill-karaoke | Yes | The card is a dark pill, so null removes that pill. |
| korean-ad | Yes | Weight-shift look with an accent on the spoken word. |
| punch, tiktok-green | No | Request with design is not supported on these two. |
Rules that apply to every override
- Colors are hex,
rgb(),rgba()ortransparent. Other CSS syntax is rejected. - A number outside its documented range returns a 400, so a wrong look fails at request time and you do not pay for an incorrect render.
- To keep the original video and only change the look, send
source_caption_idand notvideo_url. Sume reuses the stored word timings, so speech-to-text does not run twice, and the price is the same because a restyle is still a render. transparentis a different choice fromnull. The docs describenullas showing no card.
Combine it with other tokens
The design groups are colors, typography, placement, phrasing and motion. A card-free look often needs a stroke so the words read on busy footage: set colors.stroke and typography.stroke_width_px in the same request.
Check the placement.anchor_ratio, which is the center of the line as a fraction of the frame height, so the words stay out of platform UI. Sume does not state where that UI sits, so check the platform's own pages.
Sources
Related posts
More in Media tools
- Captions with no style set: Korean gets black-outline, no gold tint
If you send no style, Sume picks one from the caption text, and the spoken word gets no gold tint. Set design.colors.active to add one.
- Cheapest product video ad: six stills in a Timeline render for $0.30
Six product photos become a 15 s vertical ad with no video model: a $0.10 Timeline render plus $0.20 caption cues. $0.30 against $3.43 for five Wan clips.
- Check an AI pattern tiles seamlessly with ImageChops.offset
Shift a Sume pattern image by half its size with ImageChops.offset and measure the seam stripe. A pass or fail score before you ship a repeating background.
- Check on-screen text in a Wan 3.0 clip: video frames at exact seconds
Wan 3.0 claims text rendering in 12 languages. Before you ship, pull PNG stills at the seconds the text appears with Sume video frames and read them yourself.
Written by Sume