Event recap from 200 phone clips: Timeline's 200 slots, $0.50 render
Sume Timeline takes 1 to 200 video slots and up to 1800 seconds. A 5-minute recap of 200 attendee clips is one $0.50 render, with no per-clip trim needed.

A 5-minute recap of 200 attendee clips is a single Timeline render on Sume, billed at $0.10 per output minute, so $0.50. Timeline takes 1 to 200 video slots per render and an output length of 1 to 1800 seconds.
No AI video model is needed for this one. It is assembly only, so the bill is the render.
The fit
Two hundred slots in five minutes is 1.5 seconds each, which is right for a fast montage. Per slot, source_in and duration choose the part of each file to use, so you do not pay $0.02 per clip to trim first.
| Output length | Seconds per clip | Billed minutes | Render |
|---|---|---|---|
| 2 minutes | 0.6 | 2 | $0.20 |
| 3 minutes | 0.9 | 3 | $0.30 |
| 5 minutes | 1.5 | 5 | $0.50 |
| 10 minutes | 3.0 | 10 | $1.00 |
Practical steps
Phone clips arrive in mixed orientations. The slot fit option handles it: cover (the default) crops to fill, contain letterboxes, and blur fills the bars with a blurred copy of the clip. For a vertical recap with a few landscape clips, blur looks better than cover, which cuts the sides.
Every URL must already be hosted by Sume. Import each file first with POST /v1/media-imports. Add a music file as the audio.url, or set audio.mode to silence. A soundtrack bed with ducking needs a real spine, not silence.
Errors to expect
Timing is the usual failure. invalid_segment_timing means slot starts do not increase, and segment_overlap means slots overlap beyond the crossfade. video[0].start must be 0, and coverage can stop at most 0.5 seconds before the end of the audio.
Generate the slot list in code from a sorted file list and a fixed duration, instead of typing 200 start times by hand.
Limits
More than 12 slots render in chunks (strategy auto), which is why a 200-slot job takes longer than a short one. Submit it asynchronously, poll /v1/jobs/:id/status, and fetch /result.
Sume does not pick the best moments from 200 clips. You choose the order and the in-points. Check each person you show has agreed to appear before publishing, which is a matter for the organiser, not the render.
Rates are the Sume card on 2026-10-07; see Timeline for the live request fields.
Sources
Related posts
More in Use cases
- How do I make AI announcer intros for conference speakers?
Ten 25-second speaker intros with one shared sting cost about 43 cents on Sume: 2 cents of TTS and a 1-cent join each, plus a $0.125 track made once.
- Event storyboard animatic: ten 3-second Omni shots at 360p cost $1.13
Ten 3-second Gemini Omni Flash 1.1 shots at 360p cost $1.13 on Sume, $1.23 with a Timeline join. A cheap moving storyboard of an event for a client review.
- Facebook feed ad text 50-150 characters, headline 27: what Sume burns
Meta's Facebook feed video page lists 50-150 characters of primary text and a 27-character headline. Sume's burned captions never touch those ad fields.
- How do I make a safety briefing audio in three languages with TTS?
One 1,800-character briefing in English, Spanish and Polish is three TTS jobs: 9 cents each, 27 cents in all on Sume. Set language on every job and review it.
Written by Sume