Pet adoption video music: a 30-second hopeful shelter bed

For a shelter's pet adoption appeal, ask for a 30-second hopeful acoustic bed with ukulele and soft piano, with a warm lift at 0:18 when the adoption call to action appears. On Sume that is one generation at $0.125 and a one-minute render at $0.10, so $0.225.

An adoption appeal asks for action, so the music should be warm without being manipulative. Avoid slow, sad piano; it can make viewers scroll away. The brief aims for gentle hope: a playful start for the animal's personality, and a lift for the call to action.

The brief to send

One short named moment, the lift at 0:18, anchors the edit to the call to action.

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: pet-adoption-video-music-a-30-second-hop-001" \
  -d '{
      "model": "sume/music-auto",
      "prompt": "Hopeful shelter appeal, 96 BPM, C major. Ukulele, soft piano, light glockenspiel, soft hand percussion. Playful opening, warm lift at 0:18 for the call to action, gentle close at 0:30. Warm, natural, bright production. Instrumental, no vocals. A 30-second track."
    }'

Why each axis is set that way

Getting the length right

The router has no duration field, so the 30 seconds are in the prompt. Set audio.duration_seconds to 30 and use a short fade at the end. A shelter may want 15-second and 30-second versions; each is its own generation and its own render.

If a volunteer reads the appeal, use the voice as the spine and add duck_db.

Before paying for a render, call POST /v1/timeline-1.0/plan with the same body. It is unbilled and reports the billable minutes, which for this 30-second video is 1. Then send the real POST /v1/timeline-1.0/render with an Idempotency-Key, wait up to 30 seconds in sync mode, and poll GET /v1/jobs/:id/status if it is still queued or processing. Statuses are queued, processing, completed, failed and canceled, and a 429 queue_full means try again shortly.

What it costs

One appeal is one generation and one render. A shelter that posts a new animal every week across a year would spend about 52 times $0.225, which is $11.70, for a fresh bed each time, or $5.325 if it reuses one bed with 52 renders and generates one. Scaling is simple arithmetic. One finished video here is $0.225 of audio and assembly, so ten of them are $2.25 and fifty are $11.25, before any retries. Failed jobs are not billed as accepted generations, but a regeneration you ask for is a new job, so budget one or two extra takes for a hero clip.

Check before you publish

Test two moods against each other on a single animal; a flat price makes this cheap.

Keep winning prompts in the shelter's shared notes.

Volunteers can run this without audio skills. The workflow is a single brief, one request, and a short list of checks, and the shelter's cost stays predictable because the price per generation does not depend on the track.

The hand-off between the two calls is the step people miss. When the music job completes, GET /v1/jobs/:id/result returns result.artifacts[] with an audio/mpeg file on media.sume.com. Timeline only accepts workspace media URLs, so import any outside file through POST /v1/media-imports first, and send the resulting URL as soundtrack.url. The Music docs also note that job.request.routed_model names the engine that actually ran, which is worth saving with the file.

• Use each animal's real photos and facts; the music is not a substitute.
• Keep contact details and adoption terms in your own copy.
• Avoid sad, guilt-based moods in the prompt.
• Confirm usage terms for generated music with Sume before a paid promotion.