TikTok Smart Split vs Sume: turn a long video into vertical clips
TikTok Studio Web's Smart Split clips, reframes and captions long videos. What the same job takes with Sume trim, crop and captions, and what it does not do.

Smart Split is a TikTok Studio Web tool that automatically clips, reframes, captions and transcribes a longer video into several short videos, and Sume can do the cutting, cropping and captioning steps through its API but does not choose the moments for you. If you want one-click clip picking inside TikTok, use Smart Split; if you need a repeatable pipeline you control, use Sume's trim, filter and captions endpoints.
TikTok's description is from its newsroom post New AI-powered tools to make it easier to create and share on TikTok, dated October 28, 2025 and read 2026-10-02. Sume facts come from Video trim, Video filter, Video captions and Video inspect.
What does Smart Split do?
Per the newsroom post, it accepts videos over one minute, lets you select portions to convert, offers customisable caption formatting and vertical reframing, and can upload generated clips directly to your account. It was listed as globally available on TikTok Studio Web at launch; the post is nearly a year old, so check your own Studio for current availability.
Which Smart Split steps map to Sume?
Sume has an endpoint for each mechanical step, but the sequence is yours to orchestrate.
| Step | Smart Split | Sume |
|---|---|---|
| Pick moments | You select portions | You choose ranges; video_inspect with transcribe: true and sentence segments gives text and times to decide from |
| Cut | Automatic | POST /v1/video-trim, $0.02 per job |
| Reframe vertical | Automatic | POST /v1/video-filter crop op in fractions, $0.02 per encode |
| Captions | Customisable formatting | POST /v1/video-captions, $0.20 per job up to 60 s |
| Upload to TikTok | Direct to your account | Not offered |
How do I cut one clip and crop it to 9:16?
Trim first, then crop. A 16:9 frame cropped to a centred 9:16 column keeps 31.6% of the width (9/16 divided by 16/9 is 0.3164), so width is about 0.316 and x is about 0.342 to centre it. Crop width and height are fractions of the frame, and the compiler even-rounds for yuv420p. The filter source ceiling is 300 s, so crop short clips, not the whole talk.
curl -X POST https://api.sume.com/v1/video-filter \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: crop-916-001" \
-d '{"video_url":"https://media.sume.com/artifacts/artf_demo/clip.mp4","ops":[{"op":"crop","x":0.342,"y":0,"width":0.316,"height":1}]}'What is the catch?
A fixed centre crop does not follow a speaker who moves, because the crop rectangle is static for the clip. Smart Split's reframing is described as automatic, and Sume's docs do not describe subject tracking, so I will not claim it. Run captions after the crop so the text sits inside the new frame.
Sources over 1800 s fail trim with source_duration_exceeded, and every input must already be on media.sume.com, imported with POST /v1/media-imports. For the long-file caption path see add captions to a long video by API.
Sources
Related posts
More in Comparisons
- TikTok product avatars skip shoes, hats, sunglasses and bracelets
TikTok's Symphony help page lists products its avatars cannot show. What to try for those SKUs, and what Sume's avatar product_image does and does not claim.
- Seedance 2.5 in Symphony takes 50 references: what Sume lists
TikTok says Seedance 2.5 in Symphony takes up to 50 image, video and audio references. Sume's docs give per-model reference types, so check the catalog first.
- Together AI dynamic rate limits (429, 503) vs Sume rate_limited
Together AI publishes no fixed tiers: limits track live capacity and your recent traffic. How its 429 and 503 map to Sume's rate_limited and queue_full.
- Together AI video API alternative: Sume /v1/videos compared
Together AI's video API is create-then-retrieve with five statuses. How that maps to Sume /v1/videos, and what each side does better.
Written by Sume