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
- 6 product photos as video references: Sume models vs Vidu Q4's 15
Vidu Q4 Preview takes up to 15 image references. Sume does not list Vidu, but eight models accept reference images. See which ones and what 5 seconds costs.
- A 60 s video as six 10 s shots on two models: $33.54
Plan a 60-second video as six 10 s shots: two hero shots on Seedance 2.5 at 1080p and four on Wan 3.0 at 720p, joined on Timeline for $33.54.
- 7 UGC hook tests on Seedance 2.5 at 480p, then one 1080p winner
Test seven 6-second 9:16 UGC hooks at 480p for $11.34, then re-render only the winner at 1080p for $8.53. Total $19.87 versus $59.71 at 1080p.
- 80-second avatar script: 60+20 or 40+40, $19.60 at Plus either way
An 80-second script is over Sume's 60-second limit. At a flat per-second rate, 60+20 and 40+40 cost the same $19.60 at Plus; only the pacing differs.
Written by Sume