2026-10-04

Korean karaoke captions: korean-ad and language ko on Sume

Burn Korean karaoke-style captions with style korean-ad and language ko on /v1/video-captions: one phrase at a time, the spoken word in a heavier weight.

5 min readSume

All posts

How do you add Korean karaoke captions to a video through an API? Send the clip to POST /v1/video-captions with style: "korean-ad" and language: "ko". The docs describe korean-ad as CapCut-style Hangul karaoke for Korean speech: one short phrase at a time, lower third, with the spoken word shifting to a heavy weight.

Do not use slam, punch or tiktok-green for Korean. They draw in Latin display faces with no Hangul glyphs, and Sume rejects Korean text on them with caption_hangul_text_latin_style rather than rendering tofu boxes.

What the style does

korean-ad is weight-shift with an accent colour on the spoken word. It is not what an omitted style resolves to: an omitted style gives black-outline for Korean, so name korean-ad when you want the ad treatment. weight-shift and korean-ad animate the wght axis, which only Pretendard carries, so a static face keeps colour and scale emphasis but loses the weight travel.

Choosing among the Hangul identities

Identities from docs.sume.com Video captions, read 2026-10-04.
Style	Look
`black-outline`	White fill, thick black outline, mid-frame; the safe default
`weight-shift`	Phrase cards; the spoken word takes the weight
`highlight`	An accent block sweeps in behind the spoken word
`pill-karaoke`	Card in a dark pill; colour tracks the voice
`clip-wipe`	Each word wiped in left to right; clear at small sizes
`editorial-emphasis`	Two-line left-aligned card with a large phrase-final word

Send the request

language only tells speech-to-text what to expect; it never selects the style or the font. Add script_text if you want the burned wording to follow a script, with timings still coming from speech-to-text.

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-karaoke-001" \
  -d '{
    "video_url": "https://media.sume.com/artifacts/example/clean.mp4",
    "style": "korean-ad",
    "language": "ko",
    "design": { "colors": { "active": "#22D3EE" } }
  }'

Restyle without a second transcript

To try a different look, send 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, and billing is still a render at $0.20 for videos up to 60 seconds. If the script and the audio disagree, alignment can fail with script_alignment_mismatch; omit script_text to burn the transcribed wording.

Sources

Video captions