A 52-minute podcast on Sume: the 1800-second limit and the split
Sume trim and inspect refuse sources over 1800 seconds. A 52-minute episode must be split into two 26-minute parts first; six clips then cost about $2.50.

A 52-minute podcast video is 3,120 seconds, which is over the 1,800-second source limit on Sume's video trim and video inspect, so it fails with source_duration_exceeded. Split it into two 26-minute files (1,560 seconds each) before you import them. With that split, six vertical clips of about 50 seconds each cost roughly $2.50 at the documented rates, plus inspect compute (read 2026-10-08).
The limits that decide the split
Three Sume docs pages set the ceiling. Video trim and video inspect both cap the source at 1,800 seconds. A single trim returns 0.2 to 900 seconds. Timeline 1.0 takes an audio spine of 1 to 1,800 seconds. None of these accepts a 52-minute file, so the splitting happens in your editor before upload, then each part goes in through POST /v1/media-imports.
| Surface | Limit | Error or behavior |
|---|---|---|
| Video trim | Source up to 1,800 s; cut 0.2-900 s | source_duration_exceeded on a longer source |
| Video inspect | Source up to 1,800 s; 24 stills per call | Transcript is $0.01 per audio minute |
| Timeline 1.0 | Spine 1-1,800 s; 1-200 slots | $0.10 per ceil(output minute) |
Six clips from two halves
Pick three moments from each half. Each pass is the same: trim the range, render it to 1080x1920 on Timeline 1.0 with fit: blur or cover for a wide source, then burn captions. Detach each clip's audio first so it can serve as the spine. Keep each clip under a minute so the fixed $0.20 caption price applies. The transcript step is optional; it gives timestamps for choosing the cuts.
| Step | Arithmetic | Cost |
|---|---|---|
| Transcripts, 2 x 26 min | 52 min x $0.01 | $0.52 |
| Trims | 6 x $0.02 | $0.12 |
| Timeline renders, 50 s each | 6 x $0.10 | $0.60 |
| Audio detach for each clip's spine | 6 x $0.01 | $0.06 |
| Captions | 6 x $0.20 | $1.20 |
| Total before inspect compute | $2.50 |
Notes on the transcript line
Video inspect bills the transcript at the public $0.01 per audio minute, but also captures the job's own container compute plus a platform fee, and that compute is not priced here. Send duration_seconds as a hint (maximum 600) if you want a smaller reservation; without it Sume reserves one minute. If you already know your cut points, skip the transcript and the total is $1.98. The detach line exists because a Timeline render needs an audio spine, and audio detach turns a clip's own track into a durable file for $0.01 per job.
curl -X POST https://api.sume.com/v1/video-trim \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: ep42-part1-clip3" \
-d '{
"video_url": "https://media.sume.com/artifacts/artf_demo/ep42-part1.mp4",
"start": 812.4,
"duration": 50
}'Sources
Related posts
More in Use cases
- 90-second explainer from fifteen 6-second scenes, plus the render
Fifteen 6 s scenes at 720p cost $11.25 on Wan 3.0 or Omni and $52.00 on Seedance 2.5; the 90 s timeline render adds $0.20 (2 billed minutes at $0.10).
- Ad hook test matrix: 4 hooks x 2 ratios on Omni Flash, priced
Four ad hooks in 16:9 and 9:16 as 5-second Omni Flash drafts cost $1.50 at 360p on Sume; re-rendering two winners at 1080p adds $1.875. The full matrix.
- Adobe's Cyber 5 forecast: plan five daily Sume bulk queues
Adobe projects $47.5B for Cyber 5, 17.3% of holiday online sales. Map the five days to five Sume bulk queues with one idempotency key each and a cap per item.
- AI avatar disclosure line as the first caption cue on a Sume clip
Tavus says disclosure features are still being worked on for realistic avatars. On a rendered Sume clip you can author the label yourself with caption cues.
Written by Sume