Caption 50 videos with an API: $10.00 on Sume
Sume Video Captions is a fixed $0.20 per job for videos up to 60 seconds, so 50 Shorts or Reels is $10.00.
Captioning 50 videos on Sume costs $10.00: a fixed $0.20 per caption job. The docs price it for videos of 60 seconds at most, under the current fixed estimate, and point to GET /v1/catalog for the live price.
Source: Sume's video captions docs, read 2026-10-06. A restyle of an existing caption does not change the price, so styling experiments on the same job are not a new line item.
What does a month look like?
Captioning is one job per video.
| Videos | Cost |
|---|---|
| 50 | $10.00 |
| 100 | $20.00 |
| 200 | $40.00 |
What should I plan for?
Captions are one stage of finishing; trims, filters and the final render are billed separately.
- Keep each video at 60 seconds or less for the quoted price.
- Run captions after the final cut; a trim afterwards means a new caption job.
- Use
Idempotency-Keyper video so a retry does not double bill.
Sources
Related posts
More in Media tools
- Sume caption design overrides: one key, one change, bad value 400s
Sume video captions design overrides merge over the style, so one key changes one thing. A bad value fails with 400 at request time, before any render.
- Korean caption fonts on Sume: why weight-shift needs Pretendard
Sume's weight-shift and korean-ad caption styles animate a font weight axis that only Pretendard has. Other faces keep color and scale emphasis only.
- Captions for a voiceover: reuse TTS word timings or run STT?
If you generated the voice on Sume, ask for timestamps.words and skip a 1-cent-a-minute STT pass. If the audio is someone else's, run STT. Here is the split.
- Captions language field: a speech hint, not a style or font
On Sume video captions, language only hints speech-to-text. It never picks the style or font, so Korean needs a Hangul style such as black-outline.
Written by Sume