B-roll from a transcript: one 4-second clip per sentence
Turn a 2-minute talk into B-roll: STT for $0.02, 12 sentence clips at Wan 3.0 480p and a 2-minute Timeline render come to $3.22.
A clip for every sentence
Speech to text returns the sentences with timing. Use the 12 most visual sentences, write a prompt per sentence, and generate 4-second clips at 480p as a first pass.
| Item | Basis | Cost |
|---|---|---|
| Transcript, 2 min | STT $0.01 per audio minute | $0.02 |
| 12 clips, 4 s, 480p | Wan 3.0 at $0.0625 per second, $0.25 each | $3.00 |
| Compose 2 min | Timeline, 2 output minutes | $0.20 |
| Total | $3.22 |
Limits
STT takes audio up to 10 minutes per job, so split longer talks. Keep clips at 4 seconds so they fit the sentence they illustrate.
Sources
Related posts
More in Use cases
- Band tour teaser: Seedance 2.5 with an audio reference, $8.67 a city
A 15-second 9:16 tour teaser from two photos and a track costs $8.67 on Seedance 2.5 at 720p; three cities cost $26.01. Reference types and limits on Sume.
- Bedtime story video with a lullaby bed: Sume TTS, Lyria, timeline cost
Cost of a narrated bedtime story with a lullaby underneath: TTS for 3,000 characters, one Lyria 3.5 track, and a timeline render with soundtrack ducking.
- How do I turn an app screen recording into a Black Friday sale ad?
Trim a screen recording to 15 seconds, add a music bed and burn the offer in as captions. Four calls, $0.445 on Sume, no generative video needed.
- Black Friday image set: 8 products, 4 ratios, 4K for $6.40
Eight products in four aspect ratios at 4K is 32 images. On Nano Banana 2.1 that bills $6.40 on Sume, and $2.40 at 1K. Per-ratio plan and the 202 note.
Written by Sume