Online course trailer in 30 seconds with Seedance 2.5: beats and cost
A 30-second course trailer in one Seedance 2.5 request: beats for hook, promise and call to action, authored captions on top, about $17.33 at 720p on Sume.

A course trailer is a good fit for a single 30-second Seedance 2.5 request because you need atmosphere, not accurate on-screen detail. Write beats for the hook, the problem, the promise, the proof and the call to action, then burn the real course name and URL on with authored captions. At 720p the clip is about $17.33 on Sume plus a $0.20 caption job.
Beat plan
Thirty seconds is long enough for five clear beats of about six seconds. Keep every beat visual: the model generates scenes, not slides. Anything that must be spelled correctly belongs in captions, not in the generated frames.
- 0-6 s: hook, a learner struggling at a desk.
- 6-12 s: the problem, a messy notebook, a clock.
- 12-18 s: the turn, the learner opens a laptop and smiles.
- 18-24 s: proof, quick glimpses of finished projects.
- 24-30 s: calm end frame with room for the course title.
Request and price
BytePlus says Seedance 2.5 generates 4 to 30 second clips at 24 FPS in 480p, 720p or 1080p (BytePlus: Dreamina Seedance 2.5). On Sume the same range is exposed through the Video Router. Draft at 480p, then run the final.
| Step | Resolution | Price |
|---|---|---|
| Draft | 480p | $8.06 |
| Final | 720p | $17.33 |
| Captions (authored cues) | n/a | $0.20 |
| Draft plus final plus captions | $25.59 |
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: course-trailer-001" \
-d '{
"model": "seedance-2.5",
"prompt": "0-6s a learner frowns at a cluttered desk. 6-12s notebook and clock, tense. 12-18s the learner opens a laptop and smiles. 18-24s quick glimpses of finished projects on screen. 24-30s calm end frame, empty space on the right.",
"resolution": "720p",
"duration": 30,
"aspect_ratio": "16:9",
"mode": "async"
}'Burn the title on
Use POST /v1/video-captions with cues for the title and URL at the last beat. The docs say cues skip speech-to-text and burn exactly the copy you give, which is the path for silent clips (Video captions). If the clip has generated sound, the caption tool is unaffected by it.
Do not promise outcomes in a trailer that you cannot support; a generated learner is not a testimonial, and local advertising rules still apply to you.
Sources
Related posts
More in Use cases
- Out-of-office video message with an AI avatar: 15 seconds on Sume
Make a 15-second out-of-office video from a script: return date, contact, captions on. $2.76 on Standard plus a $0.20 caption add-on; Plus and Max too.
- Parent-teacher conference reminder in English and Spanish for $0.63
A conference reminder from one slide image in two languages: TTS, a Timeline render and captions per version. $0.6333 for both on Sume, from docs.
- Peacock vertical video ads in 2026: what to prepare before specs land
NBCUniversal says Peacock's vertical video format opens to advertisers in 2026 but lists no specs. Prepare a 9:16 master with Sume's timeline and wait.
- Performance Max image assets: three ratios, 5120 KB cap, 20 each
Performance Max wants landscape 1.91:1, square and 4:5 portrait images up to 5120 KB, 1 to 20 each. How to batch a matrix of images on Sume. Read 2026-10-03.
Written by Sume