How many cuts fit in a 3-minute Short? Timeline caps slots at 200
A 180-second Short built with Sume Timeline can have at most 200 video slots, each at least 0.2 seconds. That averages 0.9 seconds a cut. Here is the math.
A 3-minute Short rendered with Sume Timeline 1.0 can have at most 200 video[] slots, and each slot must be at least 0.2 seconds, so the fastest cut that still fills 180 seconds averages 0.9 seconds per slot. Slower than that is always allowed; faster than 0.9 seconds on average needs a shorter Short.
The limits come from the Timeline 1.0 docs (read 2026-10-06): video[] takes 1 to 200 slots, video[].duration is at least 0.2 seconds, and audio.duration_seconds runs 1 to 1800. YouTube's Shorts limit is 3 minutes.
What is the slot budget at each length?
Divide the length by 200 to get the slowest average cut a full 200-slot body can have, and by 0.2 to see the theoretical ceiling the slot cap overrides.
| Short length | Slowest average with 200 slots | Slots at the 0.2 s floor | What binds |
|---|---|---|---|
| 30 seconds | 0.15 s (below floor) | 150 | The 0.2 s floor |
| 40 seconds | 0.2 s | 200 | Both limits meet |
| 60 seconds | 0.3 s | 300 | The 200-slot cap |
| 180 seconds | 0.9 s | 900 | The 200-slot cap |
What else shapes a fast-cut Short?
Coverage may stop at most 0.5 seconds before the end of the audio spine, so the last slot has to reach almost to the end. video[0].start must be 0, and later starts must increase.
Above 12 slots, render.strategy: auto chunks the render. Explicit single is refused (render_strategy_unsafe). Chunking is automatic, so a 200-slot body needs no special setting.
How do I check a body before paying?
Send it to POST /v1/timeline-1.0/plan. It runs the schema checks and the compiler, then returns duration_seconds, segment_count, billable_minutes, and estimated_cost_usd_micros. A 180-second body shows 3 billable minutes, which is $0.30 at the public rate. It does not create a job, so a body with 201 slots fails at the plan stage for free.
Sources
Related posts
More in Developers
- How many images can I get per AI image request? Read n, don't guess
Sume's docs allow n up to 10 per call but say per-model ceilings are lower. Here is how to read each model's real n range from the catalog in one request.
- How Sume TTS splits a script into sentence ids (. ! ? only)
Sume's script source cuts sentences at periods, exclamation and question marks only, keeps every character, and numbers them sent_000000. Examples and traps.
- Huey task that polls an AI video job with schedule(delay=...)
A Huey task reads Sume's job status once and reschedules itself with task.schedule(delay=...) from next_poll_after_seconds, so no worker thread sleeps.
- Idempotency key for transcription: hash the request, avoid 409
Derive the Sume STT Idempotency-Key from a hash of audio_url, language and duration. A retry returns the same job. A changed body under that key is a 409.
Written by Sume