Christmas carol sing-along video: lyric lines as timed cues
Trim your choir's recording, then burn each lyric line as a timed caption cue so a congregation can sing along. Two jobs, $0.22 at listed rates.

To make a Christmas carol sing-along video, record the choir or a pianist, cut the take you want with video trim ($0.02), then burn each lyric line as a timed caption cue with video captions ($0.20 for a clip up to 60 seconds). Cues carry the text, a start and an end, so you control when each line appears and no speech recognition tries to guess sung words. Total at listed rates: $0.22 for a video a congregation, class or care home can read along with.
Why cues rather than automatic captions?
Automatic captions listen for speech. Sung vowels, a piano under a choir and a room echo make speech-to-text a poor guide for lyrics, and an instrumental take has no speech at all, which fails with caption_no_speech. Cues skip that step. You type the lines from your own song sheet, give each a window, and Sume burns exactly that. Pick a style such as black-outline, and use the design overrides to change colors or placement for one request.
How do you time the lines?
Play the trimmed clip and note the start of each line. Cue times are seconds on the clip you caption, so the trimmed file starts at zero. A line usually needs its window to run into the first beat of the next one so there is no blank flash. Keep each cue to one line you can read aloud in a breath.
| Step | Route | Rate |
|---|---|---|
| Cut the best take | POST /v1/video-trim | $0.02 |
| Burn lyric lines as cues | POST /v1/video-captions | $0.20 (clips up to 60 s) |
| Total | $0.22 |
What about longer carols and rights?
The caption price is stated for clips of at most 60 seconds, so split a long carol into verses and render each. To join them with a fade, put the captioned clips into a Timeline 1.0 render at $0.10 per output minute. Rights are yours to check: Sume burns whatever text you send, so use words you are allowed to display and a recording you are allowed to post.
Sources
Related posts
More in Use cases
- Course Black Friday offer clip: lesson excerpt under a price card
Trim 20 seconds of a real lesson, stack a price card above it with timeline compose, and let captions transcribe the lesson. Three jobs, $0.24 listed.
- DJ set teaser: flyer above the booth clip, lineup as captions
Stack a night's flyer over 15 seconds of booth footage with timeline compose ($0.02), then burn set times as cues ($0.20). The clip's own audio stays.
- Double-exposure portrait from two photos with Nano Banana 2.1
Blend a portrait and a landscape into one double exposure: two input_references, a pinned 4:5 ratio, Nano Banana 2.1 at 1K, and the 10-reference cap on Sume.
- eBay listing video: no URLs or calls to action, check before upload
eBay's images, videos and text policy bars contact details, links and calls to action in listing video. Check stills and speech on Sume before you upload.
Written by Sume