AI background music for a one-minute video: brief and cost
Generate a one-minute bed with the Music Router at $0.125 and render it under the video at $0.10 per output minute: about $0.225 in total.

Brief the music for a one-minute video with section markers, generate it for $0.125, and render it under the video with Timeline for $0.10 per output minute. That is $0.225 in total for a one-minute piece, assuming the render bills at the per-minute rate.
Cost build-up
| Step | Price | Running total |
|---|---|---|
| Music Router generation | $0.125 | $0.125 |
| Timeline render, 1 output minute | $0.10 | $0.225 |
| Captions, up to 60 s (optional) | $0.20 | $0.425 |
Brief it
Match sections to the edit: a quiet intro for a title, a lift at the product shot, a resolve for the call to action. Ask for an instrumental so it does not fight a voiceover.
curl -X POST https://api.sume.com/v1/music-router/generate \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: bgm-minute-001" \
-d '{
"model": "sume/music-auto",
"prompt": "Confident upbeat corporate pop, 112 BPM, C major. [0:00-0:10] Intro: soft pulse. [0:10-0:40] Build: bright keys, light drums. [0:40-0:55] Lift: full band. [0:55-1:00] Out: clean ending. Instrumental, no vocals."
}'Why the render is separate
Music Router returns the song; Timeline puts it under the video. Keeping them apart lets you swap the track without paying for another generation of the video.
Notes
- The length is steered by the prompt; check the artifact before rendering.
- Render max is 1,800 seconds per output.
- Captions are a separate call, $0.20 for videos up to 60 s.
- Reuse an Idempotency-Key when retrying to avoid a second bill.
Sources
Related posts
More in Use cases
- AI bingo cards: 24 pictures once, unique cards shuffled in code
Generate 24 picture squares with the image API one time, then produce as many unique bingo cards as you need by shuffling in Pillow. Code and a cost check.
- AI blog featured image at 16:9: 1536x864 passes, 1920x1080 does not
For a 16:9 blog featured image, gpt-image-2.5 accepts 1536x864 and 2048x1152 but not 1920x1080, because 1080 is not a multiple of 16. Checked in a table.
- AI board game tokens: transparent PNG art, circle-cropped at 300 dpi
Make board game character tokens: one anchor style, a transparent PNG per character from gpt-image-2.5, then crop to a circle in Pillow at token size.
- AI bookmark design via API: the tall 1:3 and 1:4 ratios on Sume
Bookmarks are tall strips. Only Ideogram lists 1:3 and Nano Banana 2 lists 1:4 on Sume's image catalog. A catalog check, a request and a crop to your template.
Written by Sume