Yearbook slideshow video: photos, narration and music in one render

A 90-second yearbook slideshow needs 18 photos at five seconds each, a narration track and a music bed. Render once in Timeline 1.0: 90 seconds rounds up to two minutes, so $0.20. Narration of about 1,400 characters (roughly 90 seconds spoken) costs about $0.07 and a Music Router bed $0.125, so about $0.40 in total.

Costs

Build

Upload the photos (POST /v1/assets/upload-url, PUT, then POST /v1/assets/{id}/complete) and keep them in the order you want. Each photo entry is a still with duration: 5. Use fades under one second. Narration is the audio spine, so write a script that lasts about 90 seconds, since the photos must cover the audio length to within half a second; generated music then sits underneath through soundtrack with duck_db so the voice stays clear.

Limits

Student photos are personal data, so you need consent from parents or the school before upload. Sume does not recognise names, so captions and names must be supplied by you. A slideshow has no motion; for animated pages use an image-to-video model on the key photos only.