Captions or a dub for a 45-second live-commerce clip? $0.22 vs $0.16
For a 45-second clip, translated captions cost $0.22 on Sume and a dub $0.16 at list; both together are $0.36. Pick by whose voice buyers should hear.
For a 45-second live-commerce clip, translated captions cost $0.22 on Sume and a dub costs up to $0.16, so the dub is cheaper at list; doing both is up to $0.36. The decision is not price, it is whether buyers should hear the host or a narrator, because a dub replaces the audio track.
Assumptions: a 45-second clip, 675 characters of translated speech, and a spine under 60 seconds. Caption jobs are flat at $0.20 for clips up to 60 seconds, per the Video captions docs; other rates are on the pricing page, read 2026-10-05.
Three options side by side
Each starts with detach and one minute of speech-to-text.
| Option | What buyers get | Steps | Cost, up to |
|---|---|---|---|
| Captions only | Host's own voice, translated text on screen | Detach, STT, caption job | $0.22 |
| Dub only | A narrator voice in the new language, no text | Detach, STT, TTS, concat, render | $0.162 |
| Dub and captions | Narrator plus text on screen | Dub, then a caption job | $0.362 |
How to choose
- Pick captions when the host's voice is part of the sale and buyers watch with sound off.
- Pick a dub when buyers listen while doing something else.
- Pick both for a clip that is skimmed and then played.
- A dub swaps the original track, including any music and the room sound.
Check the first clip
Play the first dubbed clip with a native speaker, and read the first burned caption for prices before you run the other eleven.
Sources
Related posts
More in Comparisons
- LTX-2.3 4K at $0.24/s on fal vs Omni 4K at $0.375/s on Sume
A 10-second 4K clip costs $2.40 with LTX-2.3 on fal and $3.75 with Gemini Omni Flash 1.1 on Sume. Here is the arithmetic, the limits, and the catch.
- Ray3.2's 16 keyframes vs Omni's two frames: what Sume can do
Luma lists up to 16 keyframes for Ray3.2; Omni takes two. On Sume you chain Omni pairs: 5 keyframes is 4 clips of 5 s, $3.76 at 1080p.
- Ray3.2 takes 16 keyframes per clip. Sume takes two frames: chain them
Luma lists up to 16 keyframes per Ray3.2 clip. Sume does not ship Ray3.2, but its first and last frame jobs chain into a keyframed shot.
- Luma Ray3.2 20 s 1080p vs MiniMax H3 Max 15 s 1080p on Sume
Luma lists Ray3.2 at 1080p for up to 20 s with 16 keyframes. Sume does not run Ray3.2; H3 Max 1080p is 5-15 s at $0.20 a second. What to use for 20 seconds.
Written by Sume