Trim pauses and reorder clips by API, like YouTube chat editing
YouTube's conversational editing trims pauses and reorders for pacing. By API: inspect the clip for free, trim ranges, then reorder slots in a Timeline spec.

YouTube describes a conversational editor in Shorts and the YouTube Create app that can automatically trim pauses and reorder for better pacing. Sume has no chat editor for YouTube, but the same edit is three API calls: probe the clip with video_inspect, cut the keepers with video_trim, and reorder them as video[] slots in a Timeline spec.
Steps are from the Sume docs for Video inspect, Video trim and Timeline 1.0, read 2026-10-01.
What does each step do?
| Step | Endpoint | Billing note |
|---|---|---|
| Look at the clip | POST /v1/video-inspect | Probe and stills are unbilled |
| Cut each keeper | POST /v1/video-trim | New MP4 per range; precision exact or keyframe |
| Reorder and join | POST /v1/timeline-1.0/render | Billed per output minute |
How do I find the pauses?
Inspect returns probe facts, stills, and optional speech-to-text; it does not return typed scenes or pause marks. So you decide the ranges from the transcript and stills, or from your own analysis, and treat them as trim inputs. The worked version is remove filler words with inspect and trim.
How do I reorder segments?
Each trimmed MP4 goes into video[] with source_in 0. Order is set by start: video[0].start must be 0 and later starts must increase. A reorder means rewriting the starts so they stay increasing for the new order. If starts do not increase, or a slot overlaps past its transition, the render is refused with invalid_segment_timing or segment_overlap.
What about the audio?
Timeline needs an audio spine whose duration_seconds sets the output length, or audio.mode: "silence". Reordered speech therefore needs a spine that matches the new order, for example sliced parts in audio.parts[]. Check cost first with the unbilled plan call, then render.
Sources
Related posts
More in Use cases
- Faceless YouTube channel from outlier videos: what Sume covers
Sume's trending search is TikTok-only, so find YouTube outliers in YouTube Studio. The long faceless build is one Timeline of up to 1,800 seconds.
- Three hook cuts for a YouTube A/B test: trim jobs and bulk runs
Sume does not run the YouTube test, but it can make the three cuts: one video-trim job per hook, then a Timeline join. Bulk Format runs scale it to 100 items.
- AI album cover generator: square art at 3000×3000
Generate square album art, then upscale: Apple recommends at least 3000×3000. On Sume, generate 2400×2400 and upscale it 1.25× to reach 3000×3000.
- AI avatar for online course videos: build and update lessons
Use an AI avatar as your online course instructor: one reusable avatar, a short talking video per section, captions, and one Timeline join per lesson.
Written by Sume