Melbourne Cup Day Tue 3 Nov 2026: a Victorian cafe hours clip

Melbourne Cup Day 2026 is Tuesday 3 November, and a Victorian cafe, pub or function room that is open, closed or taking bookings that day has about three weeks to say so. One photo of the venue becomes a short silent clip with image-to-video, and a second caption job burns the hours on as cues.

The date and holiday scope come from the Public Holidays Australia page, read on 2026-10-13. Everything about Sume comes from the docs pages under sources.

Who gets Melbourne Cup Day in 2026?

The page gives Tuesday 3 November 2026 and says the holiday is observed in all of Victoria unless a non-metropolitan council has arranged an alternate local holiday. So a venue outside Melbourne should check its council before it posts a date.

The page does not give a 2026 race time, so this post does not use one.

Which Sume calls build the clip?

Step one is a video job at POST /v1/videos. Put your photo in frame_images with frame_type set to first_frame and Sume treats the job as image-to-video; send no photo and it is text-to-video. Before you pick a model, call GET /v1/videos/models and read supported_durations, supported_frame_images and supported_aspect_ratios for it, because limits differ by model. The docs state, for example, that wan-3.0 accepts 2 to 30 seconds.

Step two is POST /v1/video-captions with the finished clip's public HTTPS URL as video_url and a cues array of text, start and end. Because you send cues, Sume does not run speech-to-text and burns your text at those times. A silent clip with no cues fails with caption_no_speech, so the cues are not optional for a silent clip. Both calls are asynchronous jobs; poll or take a webhook for the result.

What should the cues say?

Say the date and your hours first, then the booking rule. A five-cue plan for a 10-second clip:

How do you send the caption job?

This script builds the cue payload and prints it, so you can check the JSON before you post it with your own API key and the real clip URL.

import json

cues = [
    (0, 2, "Cup Day, Tuesday 3 November"),
    (2, 4, "Doors open at 11 am"),
    (4, 6, "Book your table now"),
    (6, 8, "Sweep and sandwiches on the lawn"),
    (8, 10, "See you on Cup Day")
]
payload = {
    "video_url": "https://example.com/melbourne-cup.mp4",
    "cues": [{"text": t, "start": s, "end": e} for s, e, t in cues],
}
print(json.dumps(payload, indent=2))

What can go wrong?

Host the clip at a public HTTPS URL before the caption job. Generated motion can add people, signs or racing silks to a venue photo; check the result and pick another still if it shows branding that is not yours.

If you mention a sweep or a bet, check your own licence rules; the cue is only text you wrote and Sume does not review it for that.