Repurposing TikTok and Reels to Shorts: restyle captions once, $0.20
Reposting a clip to YouTube Shorts? Keep a clean master and burn captions with Sume: $0.20 a job for up to 60 seconds, and restyles skip a second transcription.

HeyOrca's YouTube news roundup (read 2026-10-07) reports a Repurpose.io partnership for reposting TikTok and Reels videos to Shorts. A reposting tool moves the file; it does not decide whether the captions inside it suit the next platform. If the TikTok version has captions burned into the pixels, the Shorts copy inherits them, in the same place and the same style.
The fix is to keep a clean master and burn captions per platform. Sume's video captions job does that for a public HTTPS video URL: it transcribes the speech (or aligns your script_text), burns a style, and returns a captioned video.
One transcription, many looks
The first caption job on a clip transcribes the audio. After that, a restyle sends source_caption_id instead of video_url. Sume reuses the source video and the word timings it already holds, so speech-to-text does not run again. The docs say the price does not change, because a restyle is still a render.
curl -X POST https://api.sume.com/v1/video-captions \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: shorts-restyle-001" \
-d '{"source_caption_id": "vc_123", "style": "punch"}'What each platform copy costs
Each accepted standalone caption job reserves and captures $0.20, for videos of up to 60 seconds, under the current fixed estimate. GET /v1/catalog shows the live price.
| Copy | Request | Price |
|---|---|---|
TikTok version, style slam | video_url of the clean master | $0.20 |
Reels version, style tiktok-green | source_caption_id from the first job + style | $0.20 |
Shorts version, style punch | source_caption_id from the first job + style | $0.20 |
| All three | One transcription, three renders | $0.60 |
Rules to know before you repost
- The caption job needs a public HTTPS video URL that Sume can fetch; localhost, private-network, signed or private URLs are rejected.
- Latin styles (
slam,punch,tiktok-green) have no Hangul glyphs: Korean text on them returns a 400 rather than boxes. - A clip with no speech fails with
caption_no_speech; sendcuesorwordswith timings to burn authored text instead. punchandtiktok-greendo not supportdesignoverrides; the other styles do.
The one habit that matters
Export the clean master before any platform captions are added, and treat each platform file as a render of it. Then a caption change is a $0.20 restyle, not a re-edit, and the Shorts copy does not carry text laid out for a different safe area.
Sources
Related posts
More in Media tools
- Move burned-in captions up or down: restyle with source_caption_id
Change caption placement with design.placement.anchor_ratio and restyle with source_caption_id: the same word timings, no second speech-to-text run.
- Reuse one sentence twice: timeline audio split allows overlaps
Timeline audio split takes up to 20 ranges that may overlap, so one hook sentence can open and close a video without re-recording or re-synthesising it.
- Skippable in-stream bills at 30 seconds: cut a 30-second version
Google bills skippable in-stream per view at 30 seconds watched, or full length if shorter. Cut a 30-second version of a long master with video-trim.
- Split a 9-minute recording into three Reels under 3 minutes
Instagram's Reels page says Reels over 3 minutes won't be recommended to new audiences. Find sentence ends with video-inspect STT, then cut with video-trim.
Written by Sume