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.

5 min readSume
All posts

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.

Caption price and Short length (Sume docs and YouTube Help, as of 2026-10-08)
ItemValue
Standalone caption job$0.20 per accepted job
Length that price coversVideos of maximum 60 seconds
Longer videosPrice not stated in the docs
YouTube Shorts maximumUp to 3 minutes
Caption inputA 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.

Cost of captioning a 180 second Short in three pieces (computed)
StepJobsEachTotal
Trim3$0.02$0.06
Captions3$0.20$0.60
Timeline, 180 s1$0.30$0.30
All7$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

All Media tools posts

Written by Sume