Sinterklaas 2026 toy shop clip: intocht 14 Nov, pakjesavond 5 Dec

In 2026 Sinterklaas arrives in Grave on Saturday 14 November and pakjesavond is Saturday 5 December, which gives a Dutch toy shop or bookshop three weeks between the two dates. A silent clip from one shop-window photo, with Dutch cues burned on, tells customers when to order and when the shop closes for the evening.

The dates come from Sinterklaas.nl, read on 2026-10-13. Everything about Sume comes from the docs pages under sources.

What dates does Sinterklaas.nl give for 2026?

The page says Sinterklaas arrives in Grave on Saturday 14 November 2026, and that the national arrival is shown on NPO Zapp around noon. It says the Sinterklaasjournaal starts on Monday 9 November and runs nightly until pakjesavond, which falls on Saturday 5 December, a weekend, so there is no school or work the next morning.

Your own order deadline and opening hours are not on that page; they are yours to state.

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 Dutch cues say?

The docs describe Latin caption styles, and Dutch is Latin script, so ordinary Dutch text works as cue text. If you do not send style, the text sets the style; for Latin text that is slam. 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, "Sinterklaas komt op 14 november"),
    (2, 4, "Pakjesavond is zaterdag 5 december"),
    (4, 6, "Bestel voor 27 november"),
    (6, 8, "Cadeautjes voor groot en klein"),
    (8, 10, "Kom langs in de winkel")
]
payload = {
    "video_url": "https://example.com/sinterklaas.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 finished clip at a public HTTPS URL before the caption job. A shop-window photo with reflections can change under generated motion, so check the result before you caption it, and do not caption over a frame that shows another brand's lettering.

Caption text is yours to spell-check: the cue is burned as you wrote it. If the same clip must run in two languages, send two caption jobs with two cue lists rather than one long list.