Korean speech captions: korean-ad style with language ko, $0.20

For Korean speech, send language: "ko" and a Hangul style to POST /v1/video-captions. korean-ad gives the CapCut-style karaoke look; black-outline is the safe default. Each accepted job is $0.20 (a flat per-job price for videos up to 60 seconds). Latin styles slam, punch and tiktok-green have no Hangul glyphs and return 400 caption_hangul_text_latin_style instead of rendering boxes.

Picking the style

language only tells speech-to-text what to expect. It never selects the style or font, which is why you pick the style yourself.

Request

If you omit style, Korean text resolves to black-outline, not to the ad look, so name korean-ad if you want it.

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-caption-001" \
  -d '{
    "video_url": "https://media.sume.com/artifacts/example/ko-clean.mp4",
    "language": "ko",
    "style": "korean-ad"
  }'

Fonts and overrides

font selects a Hangul face for a Hangul style; sending one with a Latin style returns caption_font_requires_hangul_style. design overrides colors, typography, placement, phrasing and motion for one request, for example design.colors.active for the highlight color.

A wrong look fails at request time, so you do not pay $0.20 for a render you would reject. Korean script_text is supported if you want to burn your own wording over the speech timings.