60-minute podcast to 3 captioned clips: $1.52 on Sume
A one-hour episode, split into audio, transcribed at $0.01 a minute, cut to 3 clips and captioned costs about $1.52. OpusClip plans are $15 to $29.
Podcast clipping tools sell finding the moments; you pay a subscription for that. On the page read today, OpusClip lists a Free plan, Starter at $15, Pro at $29, which is the tier with API access, and a custom Business plan. This post prices the manual version on Sume for one 60-minute episode and three clips. The honest gap is selection: Sume does the mechanical steps, and you or an agent choose the moments.
The steps and their prices
Speech to text bills $0.01 per audio minute and takes at most 10 minutes per request, so a 60-minute episode is six requests. The timeline audio docs cap produced audio at 1,800 seconds per job and price a split at $0.01 flat, so I split the hour as two 30-minute jobs, each with three 10-minute ranges.
| Step | Rate | Amount | Cost |
|---|---|---|---|
| Split audio into 10-minute ranges | $0.01 per job | 2 jobs | $0.02 |
| Transcribe | $0.01 per audio minute | 60 minutes | $0.60 |
| Render each clip with a start offset | $0.10 per output minute | 3 clips under 1 minute | $0.30 |
| Burn captions on each clip | $0.20 per job (60 s max) | 3 clips | $0.60 |
| Total | $1.52 |
Picking the moments
Read the transcript, find three passages of 30 to 60 seconds, and use their timestamps as the in-point of each render. The Timeline video layer takes a source in-point, and the clip length is the output duration. That selection is the part OpusClip automates; here you do it by hand, or you ask an agent, which is metered separately and which I have not priced.
Costs that do not appear
- Roughly the cost of your own time reading the transcript.
- A re-render if a clip starts a word late; each retry is another $0.10.
- Captions for clips longer than 60 seconds, which the standalone captions job does not cover.
- If the episode is a video file, upload it to Sume first; a media import has its own price.
When to pay for a clip tool instead
If you publish three episodes a week and want clip suggestions, $15 to $29 for a tool that picks moments is worth comparing against your time. If you publish an episode a month and know which three minutes mattered, $1.52 is the cheaper answer.
Sources
Related posts
More in Use cases
- Slide deck to video: ten slides as Wan 3.0 reference images on Sume
Turn a slide deck into a 30 second Wan 3.0 clip on Sume by exporting up to ten slides as images. Limits, a request body, and the $3.75 cost at 720p.
- Slow, clear learner audio: Sume TTS speed 0.6 and sentence slices
Sume TTS speed goes down to 0.6. For learner audio, render at 0.8, slice by sentence with word timings, and keep the full pass for comparison. Cost per lesson.
- Sneaker drop teaser: test on Seedance 2.0 Mini, finish on 2.5
Plan a 10-second sneaker teaser: five 480p tests on Seedance 2.0 Mini, one 720p keeper on 2.5, with exact Sume prices for each step and the reason to split.
- A product sells out mid-promo: swap one Timeline slot and re-render
When a SKU in a gift-guide video sells out, change that slot's source_url, run the free plan, then re-render with a new idempotency key.
Written by Sume