Captions on a 3-minute Short: Sume's $0.20 covers 60 s, plan three
Sume's standalone caption job is $0.20 for videos up to 60 seconds. A 180 second Short, the YouTube ceiling, means three cuts, so plan about $0.96 all in.

Sume's standalone video captions job reserves and captures $0.20, and the docs say that price is for videos of at most 60 seconds. YouTube's Shorts page (read 2026-10-08) allows a Short of up to 3 minutes, so a full-length Short is three times the length the price is written for. The safe plan is three 60 second pieces: 3 captions at $0.20 is $0.60, plus 3 trims at $0.02 and a $0.30 Timeline render to join them, which is $0.96.
What the docs say
The caption docs state the price and the length it applies to. They do not state a price for a longer video, so this post does not assume one.
| Item | Value |
|---|---|
| Standalone caption job | $0.20 per accepted job |
| Length that price covers | Videos of maximum 60 seconds |
| Longer videos | Price not stated in the docs |
| YouTube Shorts maximum | Up to 3 minutes |
| Caption input | A public HTTPS video URL |
The three-piece plan
Cut the Short into three pieces of 60 seconds with video trim, at start 0, 60 and 120, each with duration 60. Caption each piece, passing script_text when you know the words so the wording follows your script and the timing follows speech-to-text. Join the three captioned files with a Timeline render of 180 seconds.
| Step | Jobs | Each | Total |
|---|---|---|---|
| Trim | 3 | $0.02 | $0.06 |
| Captions | 3 | $0.20 | $0.60 |
| Timeline, 180 s | 1 | $0.30 | $0.30 |
| All | 7 | $0.96 |
Cut points and the join
Cut at a pause in the speech, not at a fixed 60 second mark, or a word will be split across two caption jobs. Keep each piece at 60 seconds or less. If the pauses force pieces shorter than 60 seconds, you may need a fourth caption job, which adds $0.20. The captions route needs audible speech unless you send cues, and it burns text onto a clip at a public HTTPS URL. For the order of voiceover, captions and timeline in a Short, read this post, and for the trim request, this one.
When the Short is 60 seconds or less
A Short of 60 seconds or less needs one caption job at $0.20, with no split and no join. That is the case the price in the docs was written for. Only the longer Shorts, up to the 3 minutes YouTube allows, need the three-piece plan.
Check the current price at GET /v1/catalog before you build a budget, since the docs say the figure is a fixed estimate. The restyle path is cheaper: a source_caption_id re-burns an earlier caption under a new style with no second speech-to-text, and the docs say the price does not change.
Sources
Related posts
More in Media tools
- Caption 30 product videos with Sume Video captions for $6
Sume Video captions reserve and capture $0.20 per standalone job, so 30 product videos cost $6.00. Per-batch arithmetic and what the job returns.
- Caption a 45-second reel for 20 cents: script_text or speech-to-text
A standalone Sume caption job is $0.20 for a clip up to 60 seconds, so a 45-second reel is 20 cents. Send script_text to keep your exact wording.
- Caption a 75-second clip: the $0.20 estimate is for 60 seconds
Sume's standalone caption job lists $0.20 for videos up to 60 seconds. For a 75-second clip, read the live catalog price or split the cut first. Budget table.
- caption_no_speech: why a caption job fails on a silent clip
A Sume caption job returns caption_no_speech when the clip has no audible speech. The fix is cues, segments or words, not a retry.
Written by Sume