Burning Korean captions: why a Latin style returns a 400 on Sume
Sume's slam, punch and tiktok-green styles have no Hangul glyphs, so Korean copy on them fails with a 400. Which style to pick and what a $0.20 caption costs.

If your Short speaks Korean, do not pick slam, punch or tiktok-green. The Sume captions docs say those three draw in Latin display faces with no Hangul glyphs, so Korean copy sent to them returns 400 caption_hangul_text_latin_style. Sume rejects it on purpose: the docs argue a style you did not choose is worse than an error.
Which style when
- Omit style and the wording decides: slam for Latin text, black-outline for Korean.
- korean-ad is the CapCut-style Hangul karaoke look: one short phrase at a time, lower third. Pair it with language: ko.
- black-outline is described as the safe default: white fill on a thick black outline, mid-frame.
- Naming a Hangul font with a Latin style returns 400 caption_font_requires_hangul_style.
Cost and silence
Each accepted standalone caption job is $0.20 for videos up to 60 seconds under the current fixed estimate; confirm live in GET /v1/catalog. Speech-to-captions needs audible speech: a silent clip fails as caption_no_speech. For silent clips, send your own words, cues or segments with start and end seconds and no speech-to-text runs.
Restyle without paying for a second transcript
To try another look, pass source_caption_id instead of video_url. Sume reuses the source video and the word timings it already has, so no second speech-to-text runs. Billing is unchanged, because a restyle is still a render. If you are unsure which of two styles reads better on a phone, restyle once rather than guessing.
Why 60 seconds is the planning number
YouTube's Shorts guidelines say Shorts creation tools allow up to 3 minutes. The fixed $0.20 caption estimate on Sume covers up to 60 seconds, so check the live catalog before captioning anything longer.
| Speech | Style | Result |
|---|---|---|
| English | slam (default) | Works |
| Korean | black-outline (default) | Works |
| Korean | korean-ad with language ko | Works |
| Korean text | slam, punch or tiktok-green | 400 caption_hangul_text_latin_style |
Request
curl -X POST https://api.sume.com/v1/video-captions \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: ko-short-1" \
-d '{"video_url":"https://media.sume.com/artifacts/example/clean.mp4","style":"korean-ad","language":"ko"}'Sources
Related posts
More in Media tools
- Lip Sync or Native Audio for a Talking Shot: Which Sume Route
Sume's docs say video models do not lip-sync to TTS. Compare Fabric, H3 Max lip sync, Avatar Video and Kling native lip sync for a speaking shot.
- Short clip in Timeline: when does it loop and when does it freeze?
render.pad_mode auto loops a short source only when the shortfall is over 0.25 s and the clip is at least 0.5 s long. Otherwise it holds the last frame.
- Luma Ray3.2 length by frame rate (24/30/60 fps) and Sume's fps
Luma lists Modify Video at 20 s for 24 fps, 15 s for 30 fps and 7 s for 60 fps. Sume's video-trim and timeline tools output 24, 25, 30 or 60 fps.
- Mailgun's 25 MB message cap: fit a video clip or send a link
Mailgun supports messages up to 25 MB in total, attachments included. Use Sume video trim to cut a clip under that, or send a link when the video is longer.
Written by Sume