Caption micro-drama dialogue per shot: $0.20 per clip up to 60 s
Video captions cost $0.20 per job for clips up to 60 seconds. Caption each shot before assembly; a silent clip fails with caption_no_speech. Budget math.
Video captions cost $0.20 per job for a video up to 60 seconds, so captioning each 30 second shot of a micro-drama before assembly is $0.20 a shot. A clip with no speech fails with caption_no_speech, which means silent reaction shots must be skipped or given authored cues. Per-shot captions give you precise timing; one pass over the finished cut is cheaper.
Metricool's TikTok news page (read 2026-10-03) reports that micro-dramas are taking off across TikTok, Instagram Reels and YouTube Shorts. Captioned dialogue is part of how a muted viewer follows one.
Per shot against per episode
The 60 second ceiling decides it. A 90 second episode is longer than one caption job allows, so you need at least two passes either way.
| Plan | Jobs | Cost | Note |
|---|---|---|---|
| Caption three 30 s shots | 3 | $0.60 | Skip any silent shot |
| Caption two 45 s halves | 2 | $0.44 | Includes $0.04 for two trims |
| Caption the whole 90 s | 1 | Not possible | Over the 60 s limit |
Styles and authored cues
Styles include slam, punch, tiktok-green and black-outline. When you want overlays that are not speech, such as a location card or a text message, cues or segments give authored overlays. The full list is on the video captions page.
The order of operations
Caption first, then assemble, so Timeline 1.0 joins finished clips. Captions burn into pixels, so they cannot be edited afterwards.
- Generate the shots and approve them.
- Run captions on each shot that has speech.
- Join the captioned shots with Timeline 1.0 at $0.10 per started output minute.
- Check the first caption on a muted playback before posting.
What to watch
A silent shot fails with caption_no_speech and should not be retried in a loop. Check which shots have audio first with video inspect and probe.has_audio. Sume transcribes the speech it hears; it does not fix a misheard name, so proofread the names on screen.
Sources
Related posts
More in Media tools
- Caption line breaks: Netflix bottom-heavy pyramid rule vs Sume cards
Netflix wants two-line captions broken as a bottom-heavy pyramid. Sume caption cards break by phrasing settings. How to approximate the rule and where it ends.
- Captions for applause and music cues: author the cue text yourself
ElevenLabs Scribe can tag laughter and applause. On Sume, a silent clip returns caption_no_speech, so supply your own cues.
- Check a product-swap video edit for the old product with frames
After a prompted product swap on a video, pull matching stills from the source and the edit and compare them to catch the old product. Sume docs for each step.
- Check a video crop before you pay: free video-filter /check
Validate a crop or dim program with POST /v1/video-filter/check, which is free, then submit the $0.02 encode. Diagnostics, refusal codes and next_action.
Written by Sume