Toy drive drop-off video: three posters, voice, music, 47 cents
A 30-second toy drive video for your drop-off box: three Ideogram posters, one voice-over, one music bed and a Timeline render, priced at about $0.47 on Sume.

To make a toy drive drop-off video, generate three poster stills (what to bring, where the box sits, the last drop-off day), turn a short script into a voice-over, add one music bed, and assemble the stills on a Timeline. On Sume that stack prices at about $0.47 for a 30-second 9:16 clip, before any retakes. The same budget covers a shop counter, a school lobby or a church hall, and nothing in it needs a camera crew.
A drop-off box lives or dies on three facts: what to donate, where the box is, and when it leaves. Put each fact on its own still and let the voice carry the order.
What are the three stills?
Generate them with Ideogram 4.5 at medium quality, a model in Sume's image catalog. Keep each poster to one short line of text so you have less to check on every retake.
Edit the first poster with the next two as references if you want one look across all three: the Ideogram docs say that with references, the first image is edited and up to four more guide it.
- Poster 1: "New, unwrapped toys" with a simple box illustration.
- Poster 2: the drop-off spot, for example "Front desk, Main Street".
- Poster 3: the last drop-off day and the pickup partner, if you have one.
How do you add voice and music?
Write about 450 characters of script. As a rough guide, a calm read runs near 15 characters a second, so that is about 30 seconds. Sume's voice-over is billed per 1,000 characters, spaces and punctuation included.
The music bed is one Music Router generation. Put the exclusions in the positive prompt (for example, "instrumental, no vocals, warm and gentle") because the endpoint does not accept a negative prompt. Duration control is also in the prompt text, so ask for a 30-second track.
What does it cost, line by line?
Prices below are Sume's catalog numbers on origin/main, read 2026-10-11. Image prices are the provider list times the 1.25 house margin. Voice-over is computed on 450 characters and shown before Sume's rounding to whole cents.
| Line | Quantity | Unit price | Line total |
|---|---|---|---|
| Ideogram 4.5 poster, medium | 3 images | $0.075 per image | $0.225 |
| Voice-over (TTS) | 450 characters | $0.0475 per 1,000 characters | $0.0214 |
| Music Router track | 1 audio | $0.125 per audio | $0.125 |
| Timeline render | 1 output minute | $0.10 per output minute | $0.10 |
| Total | $0.4714 |
When should you run it?
Run it the week before you want boxes to fill. OPM lists Thanksgiving Day as Thursday, Nov 26 and Christmas Day as Friday, Dec 25, so work back from the day your partner collects the toys and set the box's last day a few days earlier. Put that date on the third poster and in the voice-over, so the picture and the sound agree.
If a retake is needed, regenerate only the poster that is wrong. Three images at medium cost $0.225 in total, so one retake adds $0.075, and the Timeline render is the only step you repeat after it ($0.10). Every step is an asynchronous job, so submit, poll the job until it is ready, and read the result link.
Slot timing is simple: three posters of ten seconds each fill a 30-second voice-over, with a short fade between them. Timeline accepts fades of up to one second on slots after the first, and the music bed sits under the voice. If you would rather have no music, drop that line and the total falls by $0.125.
Sources
Related posts
More in Use cases
- Travel agent itinerary video from photos, voice and music
Turn a 5-day itinerary into a 45-second video on Sume: client photos, a TTS voice-over and a music bed in one Timeline render for about 26 cents.
- Trim a self-hosted AI clip with Sume: $0.02, audio kept
Open-weights video models give fixed-length clips with sound. Import the file to Sume and cut a start-to-end range with video trim at $0.02 a job.
- Trunk-or-treat event video: plan the cost first, pull a poster frame
A church or school trunk-or-treat promo from event photos: check cost with the free plan route, render for $0.10, then pull a poster still with video frames.
- Ugly Christmas sweater party invite: card over a clip, $0.02
Float your invite card over 8 seconds of last year's party footage with timeline compose overlay: $0.02 flat, 9:16 by default, card keeps its shape.
Written by Sume