Trending TikTok metadata to a Seedance 2.5 clip
Sume's trending-videos search returns TikTok metadata for $0.10 a call, not video files. Use it to write a brief, then render an original Seedance 2.5 clip.

POST /v1/trending-videos/search returns ranked public TikTok video metadata, not downloadable files, at $0.10 per accepted call. The workable flow is to search, read the descriptions and hashtags for what is working, then write your own prompt and generate an original clip with seedance-2.5.
What the search returns
Each result carries the public watch URL, an optional cover thumbnail, description, creation time, region, author handle and nickname, metrics and relevance scores. It does not return raw TikTok video CDN URLs, and the docs say download and mirroring are reserved for a future workflow.
| Field | Notes |
|---|---|
| query | Required in production, up to 200 characters |
| platform | tiktok only |
| window | yesterday, this-week, this-month, last-3-months, last-6-months, all-time |
| limit | 1 to 50, default 10 |
| summary_mode | none, metadata or transcript (transcript returns metadata plus a warning) |
Step one: search
The response data holds a videos array. This script prints the top descriptions and builds a brief from them.
import os, requests
H = {"Authorization": f"Bearer {os.environ['SUME_API_KEY']}"}
r = requests.post(
"https://api.sume.com/v1/trending-videos/search",
headers=H,
json={"query": "desk setup", "window": "this-week", "limit": 5, "summary_mode": "metadata"},
timeout=60,
)
r.raise_for_status()
for v in r.json()["data"]["videos"]:
print(v["url"], "|", (v.get("description") or "")[:100])Step two: write an original brief
Read the descriptions for patterns: the hook, the setting, the pacing. Then write your own prompt. Do not paste another creator's caption or try to recreate a specific video. The search is research; the clip you render should be yours.
Step three: render
seedance-2.5 accepts 4 to 30 seconds at 480p, 720p and 1080p through Video Router. Draft at 480p first.
curl -X POST https://api.sume.com/v1/video-router/generate \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: desk-setup-draft-001" \
-d '{"model":"seedance-2.5","prompt":"A tidy desk setup at golden hour, slow push-in, soft ambient sound","resolution":"480p","duration":6,"aspect_ratio":"9:16","mode":"async"}'Cost of the loop
One search is $0.10. Repeat browse calls can be served from cache. The clip is billed at the model's list price times 1.25, and usage.cost on the poll response shows the amount.
Sources
Related posts
More in Models
- Veo 3.1 extend adds 7 s up to 20 times, 720p only: plan a long clip
Google's Veo docs let you extend a clip by 7 seconds up to 20 times, at 720p only. Read the arithmetic, then compare it with one-call 30 second models on Sume.
- Veo 3.1 Lite 1,024-token prompt limit vs Omni's 20,000 characters
Google's Veo 3.1 Lite page caps text input at 1,024 tokens. Sume's gemini-omni-flash-1.1 row takes 20,000 characters. What that means for long shot lists.
- Veo 3.1 Lite takes text and image only; Sume models take more inputs
Google lists Veo 3.1 Lite inputs as text and image. On Sume, Seedance 2.0 and Wan 3.0 also accept video and audio references; Kling 3 does not.
- Video aspect ratios by Sume row: Kling 3, Gemini, Wan 3.0, MiniMax H3
Which aspect_ratio values each Sume video row takes: kling-3 has three, Gemini two, Wan and MiniMax add adaptive, and MiniMax adds 21:9. From the catalog.
Written by Sume