Voiceover plus captions for a 900-word script: $0.4565
A 900-word script is about 5,400 characters: $0.2565 of text-to-speech plus a $0.20 caption job, $0.4565 on Sume.
Voicing a 900-word script and captioning the result costs about $0.4565 on Sume: $0.2565 for text-to-speech and $0.20 for one caption job.
Text-to-speech is $0.0475 per 1,000 characters, and this estimate assumes 6 characters per word, so about 5,400 characters. The caption price is the fixed per-job rate. Both come from the Sume rate card read on 2026-10-06.
How is the total built?
Two jobs, run in order: audio first, then captions on the finished cut.
| Step | Basis | Price |
|---|---|---|
| Text-to-speech | 5,400 characters | $0.2565 |
| Captions | 1 job | $0.20 |
| Total | about 6 min of speech | $0.4565 |
What should I check?
Add a spare take to the budget if the first read needs a rewrite.
- Count the real characters with
len(text)before you submit. - One text-to-speech request accepts at most 20,000 characters.
- Caption after the final cut, not before.
Sources
Related posts
More in Media tools
- Public URL or media.sume.com: which Sume media tool takes which
Sume video trim and timeline accept only media.sume.com URLs from your workspace. Captions and video upscale take a public HTTPS URL. Import first.
- Why every AI background track sounds the same: a seven-axis brief
If your AI music all sounds alike, the prompt is probably generic. Sume's Lyria brief has seven axes: emotion, genre, BPM, key, instruments, arc and era.
- Write a YouTube show description from your episode transcripts
YouTube asks you to set a show's details but lists no required fields. Pull transcripts with Sume video inspect at $0.01 a minute and draft from them.
- Why a 2-minute YouTube upload is or is not a Short in 2026
YouTube treats square or vertical uploads up to three minutes as Shorts if posted on or after October 15, 2024. What to check, and how to render one in Sume.
Written by Sume