A 90-second science explainer from stills, narration and captions
Turn six diagram stills and a 1,200-character script into a captioned class explainer for about $0.66: speech at $0.057, a $0.10 render and $0.20 captions.

A teacher can turn six diagram stills and a 1,200-character script into a captioned explainer for about $0.66. Text-to-speech is $0.057, a Timeline render for two minutes is $0.20, and captions are $0.20 for a video of 60 seconds or less.
The captions limit matters here. Sume's video captions are priced for videos up to 60 seconds, so a 90-second explainer is best split into two parts of about 45 seconds each, captioned separately.
Cost of the build
| Step | Rate | Cost |
|---|---|---|
| Narration, 1,200 characters | $0.0475 per 1,000 | $0.057 |
| Timeline render, two 1-minute jobs | $0.10 per minute | $0.20 |
| Captions, two jobs | $0.20 per job | $0.40 |
| Total | $0.657 |
Plan each still
Give each still 12 to 15 seconds for 90 seconds in total. Put one idea on each: the question, the setup, the change, the result. Timeline takes up to 200 video slots, accepts fit choices such as cover or contain, and offers transitions like fade or dissolve of under a second.
Use contain for diagrams so labels are not cropped. Cover would fill the frame and cut the edges off a chart.
Check before you share
Have a colleague read the script for accuracy. A generated voice reads a wrong formula as confidently as a right one. Compare the caption text with the script, since the captions come from speech recognition unless you send your own.
Sources
Related posts
More in Use cases
- Clean a transcript with a 2,000-character instruction, then caption
ElevenLabs speech to text can edit a transcript from a natural-language instruction up to 2,000 characters. A cleanup then captions workflow with Sume captions.
- Coffee or tea pouch photos with AI: zip top, crimp and print
Pouches have a crimped top, a zip and a window. Stage them on a counter with Sume's image API and check the seal, the print and the shape before publishing.
- Course welcome video captions in your brand color (slam, $0.20)
Burn captions in your school's accent color: set design.colors.active on the slam style. It does not work on punch or tiktok-green. $0.20 for clips to 60 s.
- Article 50: creator duties vs provider duties, side by side
Article 50(4) puts deepfake and certain text disclosure on deployers, while 50(2) puts marking on providers. A two-column split for teams that publish AI video.
Written by Sume