4K vertical Short in Timeline: the 2160 cap and 1214x2160
Timeline output width and height top out at 2160 and must be even, so 2160x3840 is refused. What the largest 9:16 frame is and whether a Short needs it.
Sume Timeline accepts output.width and output.height as even integers from 256 to 2160. A 2160x3840 vertical frame is outside that range and is refused. The largest 9:16 frame under the cap is 2160 tall by 1215 wide, and 1215 is odd, so the nearest valid frame is 1214x2160 (about 0.562, versus 0.5625 for exact 9:16). Read from the Timeline docs on 2026-10-06.
Do I need more than 1080x1920?
For Shorts, YouTube's page asks for square or vertical and up to three minutes, and does not require 4K. Most viewing is on phones, where 1080x1920 is the default Timeline frame. Choose 1214x2160 only when a downstream step crops or zooms into the frame.
How do I pick the frame size?
| Frame | Valid | Note |
|---|---|---|
| 1080x1920 | Yes | Default |
| 1214x2160 | Yes | Largest near-9:16 under the cap |
| 1215x2160 | No | Odd width |
| 2160x3840 | No | Above 2160 |
How do I check before paying?
The unbilled plan call validates the schema and the compile without creating a job, so a bad size fails there for free.
Sources
Related posts
More in Developers
- video_analyze or video_segment not in Sume tools_list? Dev host only
Sume's docs list video_analyze and video_segment as dev-only, shown only when a flag is on. On mcp.sume.com use video_inspect for what is in a clip.
- video_url on Sume video: only Omni edit, Genjutsu and Recast take it
On the Sume video API, video_url is a source clip, taken by gemini-omni-flash-1.1 (edit), higgsfield-genjutsu and h3-max-recast. Others use reference_video_u...
- Voice one script in six languages: Sume TTS loop and 409 guard
MAI-Voice-2.1 sells one voice across 23 languages. On Sume, set language per line, handle the 409 voice-language guard and price a six-language batch.
- Voiceover for shorts: one sentence per shot using TTS sentence slices
Ask TTS for timestamps.words and sentence segmentation and Sume returns gapless per-sentence slices, so each shot in a short gets its own audio file.
Written by Sume