Podcast clip pipeline: $0.24 per 60-second captioned clip
Cut a captioned clip from a long recording on Sume: detach audio, transcribe, trim the video, caption it. Four API calls and $0.24 per clip, itemised.
A captioned 60-second podcast clip costs $0.24 on Sume, once you know which minute you want: $0.01 to detach audio, $0.01 to transcribe a minute, $0.02 to trim the video and $0.20 to burn captions. The expensive step is picking the moment, and that part is yours or your agent's.
The four calls
All hosted inputs must already be on media.sume.com; import the episode first.
| Step | Endpoint | Cost |
|---|---|---|
| Detach the hook window | POST /v1/audio-detach with a range | $0.01 |
| Transcribe that audio | POST /v1/stt-1.0/transcribe | $0.01 per minute |
| Trim the video | Video trim | $0.02 |
| Caption the clip | POST /v1/video-captions | $0.20 |
| Total per clip | $0.24 |
Finding the moment
Transcribe a wider window, read the text, and choose start and end times from the words. A 10-minute window is one STT job at 10 audio minutes, so it adds a dime, not a dollar. Then trim exactly that range.
Detach once per window, not once per candidate: the docs say to detach once and split later when you need many ranges.
At episode scale
One 60-minute episode, six clips, transcribing the full hour first:
| Line | Cost |
|---|---|
| 4 detach jobs (900 s each) | $0.04 |
| 60 min STT (six jobs at the 10-minute maximum) | $0.60 |
| 6 trims | $0.12 |
| 6 caption jobs | $1.20 |
| Total | $1.96 |
Check before running
Caption jobs are priced for videos up to 60 seconds; a longer clip may price differently, so read GET /v1/catalog. A caption job on a silent clip fails with caption_no_speech.
Sources
Related posts
More in Use cases
- Podcast teaser video: Omni cover-art clip plus your audio
Omni Flash makes its own sound and takes no audio upload. How to make a 9:16 podcast teaser on Sume: animate cover art for $1.00, then bring in your own audio.
- Product demo from one packshot: Omni Flash first-frame request
Turn a product photo into an 8-second demo clip with sound using Gemini Omni Flash 1.1 on Sume: the frame_images request, 1080p price, prompt tips.
- Recipe step clips: six 5 s Kling 3 shots, $4.20 silent, $6.30 sound
Six 5-second Kling 3 step clips for a recipe page cost $0.70 each silent, $1.05 with sound on Sume. When sound is worth it and where to cut costs.
- One set of clips for Reels and TikTok: three hook orders, one script
Generate five clips once, then render three opening orders with Timeline 1.0 to test which hook holds. A Python slot generator and the cost of each variant.
Written by Sume