Wine tasting invite video: Wan 3.0, 9:16, 12 s, audio reference
A 12-second vertical invite on Wan 3.0 costs $0.75 at 480p and $1.50 at 720p on Sume, and takes up to 5 audio references. Age gates and limits.

A 12-second 9:16 invite on Wan 3.0 costs $0.75 at 480p, $1.50 at 720p and $3.00 at 1080p on Sume. Pin the resolution, since Wan 3.0 defaults to 1080p when none is given. Wan 3.0 takes up to 5 reference audio files with 15 seconds in total, so a short piano or jazz loop can set the pace.
What goes in the request
An invite needs a mood and a date: candlelight, glasses, a cellar. Photos of your actual tasting room go in as reference images, up to 10. Alibaba's launch post, read 2026-10-08, lists audio among Wan 3.0's inputs but says audio texture is improving and not yet where they want it, so use your own recorded track.
Sume lists Wan 3.0 at 2 to 30 seconds, 480p, 720p and 1080p, with 9:16 among the aspect ratios and an optional end frame.
Price table
Sume bills the provider list price times 1.25, rounded up to the cent per job.
| Length | 480p | 720p | 1080p |
|---|---|---|---|
| 8 s | $0.50 | $1.00 | $2.00 |
| 12 s | $0.75 | $1.50 | $3.00 |
| 15 s | $0.94 | $1.88 | $3.75 |
Alcohol marketing rules
Alcohol advertising is regulated in many places, with age-gating and content rules on the platforms you post to. Check the rules for each platform and country before you run a promotion. I have not summarised them here because they differ and change; the checks below are for the video, not the legal review.
- Do not generate people who appear under the legal drinking age.
- Put the date, address and RSVP link in text overlays, not in the prompt.
- Draft at 480p, $0.75, and judge the music pacing before the 720p final.
- Reference audio must be 15 seconds or less in total.
Submit it and read the result
Sume reserves the billable amount from your workspace USD balance when the job is submitted, then returns a polling_url. Add the music loop as an audio_url entry in input_references once the draft prompt is right. Poll the job until status is completed or failed; a completed job lists its files in unsigned_urls.
import os
import time
import requests
H = {"Authorization": f"Bearer {os.environ['SUME_API_KEY']}"}
body = {
"model": "wan-3.0",
"prompt": "A slow push-in on the scene, soft natural light",
"duration": 12,
"resolution": "480p",
"aspect_ratio": "9:16",
}
r = requests.post("https://api.sume.com/v1/videos", headers=H, json=body, timeout=60)
r.raise_for_status()
url = r.json()["polling_url"]
while True:
job = requests.get(url, headers=H, timeout=30).json()
if job["status"] in ("completed", "failed"):
break
time.sleep(10)
print(job["status"], job.get("unsigned_urls"))Limits
Wan 3.0's file and web link inputs are not exposed on Sume, and neither is the thinking toggle. I did not test glass and liquid rendering, and the vendor pages I read do not make a claim about it.
Sources
Related posts
More in Use cases
- Yoga class promo video: three beats in one 10-second clip
A studio promo in 9:16 with Gemini Omni Flash: three timecoded beats in 10 seconds, calm native sound in the prompt, $1.25 at 720p on Sume.
- YouTube AI disclosure: a clip of someone giving advice they never gave
YouTube's disclosure page lists making someone appear to give advice they never gave. Its examples in a table, and what Sume trims and captions change.
- Shorts ads: Google says sound lifts conversions 20%+, add a bed
Google's Shorts ad page says sound lifts conversions by over 20%. Add a music bed that ducks under a voiceover with the Sume Timeline soundtrack field.
- Tutorial b-roll with Omni: six 10-second inserts for $7.50
One minute of b-roll for a how-to video is six Omni inserts of 10 seconds: $7.50 at 720p on Sume. Veo 3.1 clips run 4, 6 or 8 seconds, so the count changes.
Written by Sume