Naver Clip video: a 9:16 Sume clip with Korean captions
Making a vertical 9:16 clip for Naver Clip? Generate it on Sume, then burn Korean captions with the korean-ad style and language ko.

Generate the source clip vertical (9:16) and add Korean captions after generation. On Sume that is two calls: a video job with aspect_ratio set to a vertical value the model lists, then a caption job with style: "korean-ad" and language: "ko". Confirm Naver's current format rules on its own pages first.
Check Naver's rules
Format and monetization rules for Naver Clip are set by Naver and can change. This post does not restate them; confirm the current requirements on the Naver Clip page before you plan a campaign.
Step 1: a vertical clip
Ask GET /v1/videos/models which aspect ratios each model supports in supported_aspect_ratios; the documented example for seedance-2 lists 9:16. Limits are per model, for example seedance-2.5 accepts 4 to 30 seconds. Submit with Idempotency-Key so a retry returns the original job.
curl -X POST https://api.sume.com/v1/videos \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: naver-clip-001" \
-d '{
"model": "seedance-2",
"prompt": "A vertical UGC-style product clip on a desk, natural light",
"aspect_ratio": "9:16",
"resolution": "720p",
"duration": 8
}'Step 2: Korean captions that fit
Latin caption styles have no Hangul glyphs. Sume rejects Korean copy sent to slam, punch or tiktok-green with a 400 rather than drawing tofu boxes. For Korean speech use a Hangul style. korean-ad is the ad karaoke look: one short phrase at a time in the lower third, with the spoken word shifting to a heavy weight.
The clip needs audible speech for speech-to-captions. A silent clip fails as caption_no_speech; pass cues with text, start and end to burn authored copy instead.
curl -X POST https://api.sume.com/v1/video-captions \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: naver-clip-captions-001" \
-d '{
"video_url": "https://media.sume.com/artifacts/example/clip.mp4",
"style": "korean-ad",
"language": "ko"
}'Cost and limits to remember
A standalone caption job reserves and captures $0.20 USD for videos up to 60 seconds under the current fixed estimate; confirm live pricing in GET /v1/catalog. The video_url must be a public HTTPS URL, so use the Sume artifact URL from the first job. font is optional and only valid on Hangul styles.
Posting is outside Sume
Sume generates and captions the clip. Uploading to Naver, and anything attached to it there, happens inside Naver's tools, outside the API.
Sources
Related posts
More in Use cases
- Near-duplicate AI images: perceptual-hash dedupe before human review
Four-up image batches often contain near twins. Use a 64-bit difference hash in Pillow to drop duplicates before a person reviews them. Python for Sume results.
- Neighborhood holiday lights clip for agents from three street photos
A real estate agent's neighborhood lights tour from three of your own street photos: three 4-second Wan 3.0 shots at 480p and a join, about $0.85 on Sume.
- Netflix Ads: 10-75 s at 16:9 1920x1080, render 16:9 native
Netflix Ads video specs: 16:9 at 1920x1080, 10 to 75 seconds, H.264. Render 16:9 natively on Sume and sequence clips for longer spots.
- Recut a Christmas clip into a New Year sale ad for $0.30
A Timeline render at $0.10 and a caption job at $0.20 turn a finished Christmas clip into a New Year sale cut. Three variants cost $0.90.
Written by Sume