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
- 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.
- Binge cut: join ten AI micro-drama episodes into one video
Ten one-minute episodes become one 10-minute video in a single Timeline 1.0 render: detach each episode's audio, join the parts, and expect a $1.00 render fee.
- 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.
- How do I make a Black Friday video ad with no product photos?
Three 5-second Wan 3.0 text-to-video clips, a music bed, one render and burned-in deal text: $2.315 on Sume at 720p, no photo shoot needed.
Written by Sume