Narrate 10 slides: one Sume TTS job or ten, and what rounding costs
Ten 80-character slide lines cost 10 cents as ten Sume jobs and 4 cents as one 800-character job. When splitting is worth the extra cents, and when it is not.

A 10-slide explainer with one short line per slide is a common narration job. Sume TTS charges $0.0475 per 1,000 characters, rounded up to the next cent for each job, with a one-cent minimum. An 80-character slide line costs only 0.38 cent of audio, but a job has to be paid at no less than 1 cent. Ten of them is $0.10. The same 800 characters as a single job is $0.04.
Pricing the two layouts
| Layout | Jobs | Cost | Extra vs one job |
|---|---|---|---|
| One job, 800 characters | 1 | $0.04 | - |
| Five jobs, two slides each | 5 | $0.05 | $0.01 |
| Ten jobs, one slide each | 10 | $0.10 | $0.06 |
Why you might still split
One job is cheapest, but it gives you one audio file. To start each slide's audio at a known time, you either need the segment boundaries inside the file or one file per slide. Sume's TTS can emit sentence-level segments for timing; ten jobs give you ten independent files you can retake one at a time without touching the rest, which is the real reason to pay the extra $0.06.
Rule of thumb
- Slides whose lines are under about 210 characters round to the one-cent minimum each, so a one-line-per-job layout costs a cent a line.
- If you retake often, a per-slide job saves regenerating the others.
- If the narration is one continuous read, send one job. The cap is 20,000 characters, far above a 10-slide deck.
Sources
Related posts
More in Use cases
- Make a Top 5 vertical video from five stills with Sume Timeline
Five images, a 30-second silent Timeline at 1080x1920, then burned captions: the slot math, the still-motion limit and the cost in Sume.
- Tote bag mockup with an AI image API: your logo on a canvas bag
Send your logo as a reference to GPT Image 2.5 on Sume and ask for a canvas tote on a plain studio set. Check the logo against the original before you list it.
- Two-camera podcast clip for Shorts: alternate angles with source_in
Cut between two camera files against one audio spine in Timeline 1.0: equal on-spine starts and source_in keep both angles in sync. Python builder included.
- Two voices, one conversation: Sume TTS jobs joined by concat
Make a two-person dialogue file with Sume: one TTS job per line using two avatar voices, then one Timeline audio concat. Cost, code and the gap.
Written by Sume