TikTok title 2200 UTF-16 runes vs burned-in captions from Sume
TikTok's Direct Post title allows 2200 UTF-16 runes. Burned-in captions are separate video pixels: Sume's video-captions job burns the exact cues text you pass.

The two are unrelated fields: the post title is text you send to TikTok ("The maximum length is 2200 in UTF-16 runes"), while burned-in captions become pixels inside the video. Sume's POST /v1/video-captions burns exactly the cues text you pass, so your on-screen words are never limited by, or copied from, the title.
What does the title limit count?
TikTok states the limit in UTF-16 runes. Measure the length in your own code with the same unit before you send the title.
| Item | Where it lives | Limit stated |
|---|---|---|
| Post title | TikTok Direct Post field | 2200 UTF-16 runes |
| Burned captions | Pixels in the MP4 | None stated; job covers up to 60 s at $0.20 |
| Authored text | cues or segments with text, start, end | Skips speech-to-text |
How do I burn exact words?
Pass cues (or segments) with text, start and end in seconds. That skips speech-to-text and burns exactly that copy at those times. This is also the route for silent clips, which otherwise fail as caption_no_speech. script_text, words, cues and segments are mutually exclusive.
curl -X POST https://api.sume.com/v1/video-captions \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: caption-cues-001" \
-d '{
"video_url": "https://media.sume.com/artifacts/artf_demo/clean.mp4",
"cues": [
{ "text": "Three steps", "start": 0, "end": 2 },
{ "text": "Step one", "start": 2, "end": 4 }
]
}'Can I upload an SRT file?
No. The docs say SRT uploads are unsupported; pass phrase-level text as cues or segments. Convert an SRT into cues in your own code. A standalone caption job costs $0.20 for videos up to 60 seconds under the current fixed estimate; confirm the live price in GET /v1/catalog.
What do I still do myself?
Write the post title and send it in the Direct Post call. Sume does not post to TikTok or count runes. If you flag AI-generated content, TikTok's reference describes a separate is_aigc field that is set in that same call.
When should I burn captions at all?
Burn them when the words must be visible whatever the viewer's settings, for example a silent hook or a translated line. Keep them out of the title when the title has its own job. The caption styles are named in the docs (slam, punch, tiktok-green, korean-ad), and design.placement.anchor_ratio sets the line centre as a fraction of frame height.
Sources
Related posts
More in Use cases
- TikTok AI video of a real person without consent: the rule
TikTok does not allow AI likenesses of private figures, including anyone under 18, without consent. How Sume's prompt, props and image avatar inputs relate.
- TikTok Shop BFCM 2026 product videos: accurate, then batched
TikTok Shop's 2026 BFCM guide asks for accurate, not misleading product videos. Build one packshot-based video per SKU in a bulk run, then review each.
- TikTok significantly edited content: which Timeline edits count
TikTok's AI content rules name rearranging clips, cutting phrases and speed changes as significant edits. See which Timeline and trim steps fall on that list.
- Smart+ Catalog Ads creative: feed Auto-Crawl product videos
TikTok's Catalog Auto-Crawl finds product images and videos on public landing pages. Put videos there: generate one per product from its URL with a Sume Format.
Written by Sume