Brand-color captions on 3 ad cuts with one design key: $0.60
Set colors.active to your brand hex on the Sume caption job. Three cuts cost 3 x $0.20 = $0.60, and a bad value fails with a 400 before you pay for a render.
To put your brand color on captions, send design.colors.active with a hex value on the Sume caption job. Three ad cuts at the fixed $0.20 per caption job cost $0.60 (read 2026-10-08), and an invalid value returns a 400 at request time, so you do not pay for a wrong render.
What design can change
A caption style is a set of design tokens. design overrides those tokens for one request and Sume merges each field over the style's value, so one key changes one thing. Colors may be hex, rgb() or rgba(), or transparent; other CSS syntax is rejected and never reaches the render document.
| Group | Fields |
|---|---|
| colors | base, active, stroke, accent, accent_deep, card |
| typography | base_weight, active_weight, active_scale, font_size_ratio, safe_width_ratio, stroke_width_px |
| placement | anchor_ratio, landscape_anchor_ratio |
| phrasing | max_words, max_chars, pause_seconds |
| motion | enter_seconds, exit_seconds, emphasis_in_seconds, emphasis_out_seconds |
The one catch: two styles ignore it
punch and tiktok-green do not support design; they render on a path that reads none of these tokens. Use slam for Latin text or a Hangul style such as black-outline for Korean speech. Hangul text on a Latin style returns caption_hangul_text_latin_style, and a Hangul font on a Latin style returns caption_font_requires_hangul_style.
Three cuts, one look
Keep one JSON design object and apply it to the 9:16, 1:1 and 16:9 cuts so the accent matches. The placement fields are fractions of frame height, so a landscape cut can use landscape_anchor_ratio without touching the vertical one.
| Line | Arithmetic | Cost |
|---|---|---|
| Caption job, 9:16 cut | $0.20 | $0.20 |
| Caption job, 1:1 cut | $0.20 | $0.20 |
| Caption job, 16:9 cut | $0.20 | $0.20 |
| Total | 3 x $0.20 | $0.60 |
curl -X POST https://api.sume.com/v1/video-captions \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: brand-caption-9x16" \
-d '{
"video_url": "https://media.sume.com/artifacts/artf_demo/cut-9x16.mp4",
"style": "slam",
"design": { "colors": { "active": "#22D3EE" } }
}'Restyling without a second transcript
If the first look is wrong, send source_caption_id instead of video_url. Sume reuses the source video and its word timings, so speech-to-text does not run twice. The restyle is still a render, so the price stays $0.20.
Sources
Related posts
More in Use cases
- Brewery label that comes alive: Kling 3 first and last frame, 84 cents
Kling 3 on Sume takes a first and last frame, so a 6-second label animation that ends on the finished label costs $0.84 silent, $1.26 with sound.
- Captioning 250 holiday clips costs $50.00 at Sume's current estimate
A Sume caption job is $0.20 for clips up to 60 seconds at the current fixed estimate. What 100, 250 and 500 clips cost, and how to confirm the live price.
- Charity appeal video, 20 s on Wan 3.0: $1.25, $2.50 or $5.00
A 20-second appeal on Wan 3.0 costs $1.25 at 480p, $2.50 at 720p and $5.00 at 1080p on Sume. Which tier to publish and how many photos you can send.
- Clean studio look from a phone photo for a listing: edit cost by model
Turn a cluttered phone photo into a clean listing shot with an image-to-image call. 200 edited photos cost $1.93 to $20.00 on Sume depending on the model row.
Written by Sume