A podcast hour cut into six 1-minute clips costs $2.52 on Sume
Transcribe 60 minutes, trim six clips, caption each and render six one-minute timelines: $2.52 on Sume, line by line from published per-job prices.
Cutting an hour of audio into short clips is a pipeline of small, fixed-price jobs. Using the per-job prices on the Sume API rate card, this post totals one episode: 60 minutes in, six clips of one minute each out. The result is $2.52. The workload is an assumption (six clips, one minute each) and the prices are the published ones.
Trim and captions prices come from the Sume catalog; the other lines are on the rate card. Each tool bills separately.
Line by line
| Step | Unit price | Quantity | Cost |
|---|---|---|---|
| Speech-to-text | $0.01 per audio minute | 60 minutes (6 jobs of 10 min) | $0.60 |
| Video trim | $0.02 per job | 6 jobs | $0.12 |
| Captions | $0.20 per job (video up to 60 s) | 6 jobs | $1.20 |
| Timeline render | $0.10 per output minute | 6 output minutes | $0.60 |
| Total | $2.52 |
Where the money goes
Captions are $1.20 of the $2.52, almost half, because they are a flat price per job. Transcription is the smallest piece at $0.60. Trimming is a rounding error at $0.12.
Two limits shape the plan. STT jobs accept up to 10 minutes of audio, so an hour is six jobs. Captions are priced for videos up to 60 seconds, which is why the clips here are exactly one minute. A longer clip would need a different plan.
Scale the same shape: 20 episodes a month is $50.40, at the same assumptions. Pricing basics and balance behaviour are in the billing and credits docs.
- Plan clip length around the 60 second caption limit.
- Transcribe once; reuse the transcript for every clip.
- Add generation costs separately if the clips include new video.
Sources
Related posts
More in Pricing
- Podcast shorts in 3 markets: 20 clips a month, $12.80 on Sume
Four episodes a month with five clips each, captioned for three markets, is 20 clips and 60 caption jobs: $12.80 on Sume at list, with free translation.
- Price a 12-script ad library: MAI-Voice-2.1, Flash and Sume TTS
Twelve ad scripts from 90 to 1,200 characters cost $0.35 on Sume, $0.1386 on MAI-Voice-2.1 and $0.0945 on Flash. The per-job rounding is where they differ.
- Price a 20-prompt video regression suite: 360p, 3 seconds on Sume
A 20-prompt golden set rendered at 360p and 3 seconds on Gemini Omni costs $2.40 per run on Sume. The arithmetic, a Python cost check and the request body.
- Price before you pay: four places Sume shows a cost before a job runs
Video models list pricing_skus, Timeline plan returns an estimate, video-filter check is free, and the usage ledger shows the reserve. Where to look and when.
Written by Sume