Subtitles: how many words per line with design.phrasing
Sume video captions let design.phrasing set max_words (1-12), max_chars (4-60) and pause_seconds (0.05-3) per phrase. Not supported on punch or tiktok-green.

With Sume video captions, design.phrasing sets how much text shows at once: max_words, max_chars and pause_seconds. The API schema bounds them at 1 to 12 words, 4 to 60 characters and 0.05 to 3 seconds of silence. There is no single right number; pick by style and frame width.
Fields are from the Video captions docs and the API schema, read 2026-10-01. Blackmagic's Resolve 21.1 release added subtitle support to Cloud Presentations; here the captions are burned into the video.
What do the three phrasing fields do?
The OpenAPI descriptions are short: words per on-screen phrase, characters per on-screen phrase, and silence that breaks one phrase into the next.
| Field | Meaning | Allowed range |
|---|---|---|
max_words | Words per on-screen phrase | 1 to 12 |
max_chars | Characters per on-screen phrase | 4 to 60 |
pause_seconds | Silence that breaks one phrase into the next | 0.05 to 3 |
Which styles accept it?
design is not supported on punch or tiktok-green, which still render on a path that reads none of these tokens. Use slam or one of the Hangul styles. Numbers outside their range are a 400, so a bad look fails at request time instead of billing a wrong render.
How do I set shorter phrases?
Each field merges over the style's own value, so one key changes one thing. This sample keeps everything else and shortens phrases to three words.
The korean-ad style already shows one short phrase at a time; see design overrides on punch and tiktok-green for the unsupported styles.
curl -X POST https://api.sume.com/v1/video-captions \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: captions-phrasing-001" \
-d '{
"video_url": "https://example.com/clean.mp4",
"style": "slam",
"design": { "phrasing": { "max_words": 3, "max_chars": 24 } }
}'Sources
Related posts
More in Developers
- Subtitle position on video: Sume anchor_ratio for captions
Move burned-in captions up or down with design.placement.anchor_ratio, and set a separate landscape_anchor_ratio. A fraction of frame height, per request.
- Editorial two-line video captions: the editorial-emphasis style
Sume's editorial-emphasis caption style is a left-aligned two-line card where the phrase-final word drops to a second line at about twice the size.
- Burned-in caption text size and outline: Sume design fields
Set burned-in caption size, weight and outline per request with the six `design.typography` fields on POST /v1/video-captions. What each does and what fails.
- Cartesia accent field: multilingual voices only; Sume uses voice id
Cartesia's accent field is for multilingual voices only and works independent of locale. Sume's TTS request has no accent field: pick a voice id and language.
Written by Sume