Nonprofit year-end impact recap from five photos for Giving Tuesday
A 50-second year-end recap for a nonprofit from five photos: voice-over, music bed, one Timeline render and captions. $0.4678 on Sume, from docs.

A nonprofit can make a 50-second year-end impact recap from five photos it already has, for $0.4678 on Sume: one voice-over of about 900 characters at $0.04275, one music bed at $0.125, one Timeline render at $0.10 and one caption job at $0.20. No video generation is involved, so the figure does not grow with length until the render passes a minute.
Giving Tuesday 2026 falls on 1 December, the Tuesday after Thanksgiving, so the recap has to be ready in the week before. This post covers what to put in the five slots and what each step costs. It does not state a donation outcome, because no source in this post supports one.
Five photos, five sentences
Write one sentence per photo, about 180 characters each, 900 in all. Use numbers only from your own records: meals served, trees planted, students tutored. Spoken digits are more error-prone than words, so write them as words in the script. TTS 1.0 prices at $0.0475 per 1,000 characters with spaces and punctuation counted, so 900 characters is $0.04275, and a job may run up to 20,000 characters (models overview).
Stills as slots
Timeline treats a still as a static hold, and slots are ordered with a start and duration, with video[0].start equal to 0. Give each photo a 10-second slot with a fade or dissolve transition from the second slot on. Use fit: cover for photos that match the vertical frame and blur for landscape photos you do not want cropped. Motion on a still is accepted and ignored, with a soft warning (Timeline).
Music under the voice
Generate one instrumental through the Music Router at $0.125 per generation and add it as the soundtrack. With a real voice spine, duck_db of 0 to 20 lowers the bed under speech, and fade_out_seconds up to 10 closes the piece (Music Router). Keep the bed low enough that the numbers in the script stay clear.
Captions and the total
Burn captions from script_text so your wording, including the organisation name, is not guessed by speech recognition: $0.20 per job (video captions).
| Line | Basis | USD |
|---|---|---|
| TTS, 900 characters | $0.0475 per 1,000 | $0.04275 |
| Music bed | $0.125 per generation | $0.125 |
| Timeline render, 50 s | $0.10 per output minute | $0.10 |
| Caption job | $0.20 per job | $0.20 |
| Total | $0.46775 |
Reusing the build
A second cut for donors who gave more than once only changes the script and one or two photos: about $0.35 after the music is reused. Run the Timeline plan endpoint first: it is unbilled and returns duration and estimated cost before you commit.
Related posts
More in Use cases
- Digital Omnibus timeline: June 16 to July 27 in order
A dated list of the EU Digital Omnibus steps as reported in 2026, from Parliament on June 16 to entry into force on July 27, with the Art. 50(2) grace date.
- One 9:16 master for Instagram ads: what two Meta pages say
Meta's Instagram Feed video ad page lists 9:16 at 1080x1920 and 4 GB. Its placement chart shows a narrower Feed range. How to pick a master and check it.
- 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.
- 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