Holiday sale instrumental on Music Router: length in the prompt
Generate an instrumental sale-reel track with Sume Music Router: duration fields are rejected, so state length and structure in the prompt.

Length goes in the words
To make a track for a holiday sale reel, send a prompt to POST /v1/music-router/generate. The duration and duration_seconds fields are rejected, so steer length in the prompt, for example "a 30-second track" or timed section lines such as [0:00-0:30] Intro: ....
With model omitted or set to sume/music-auto, Sume picks the engine (Lyria 3.5 today). The job result names the engine that ran under job.request.routed_model.
Request
curl -sS -X POST https://api.sume.com/v1/music-router/generate \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: sale-track-001" \
-d '{
"model": "sume/music-auto",
"prompt": "Upbeat acoustic pop with sleigh bells, 110 BPM, a 30-second track. Bright intro, a lift at 0:12, resolve on a clean final beat. Instrumental, no vocals."
}'Fields
Put exclusions in the positive prompt, because negative_prompt is unsupported when non-empty. You can also pass an image_url (public HTTPS) as a mood reference.
| Field | Notes |
|---|---|
| prompt | required, 1 to 5000 characters |
| model | sume/music-auto (default), lyria-3.5 or lyria-3-pro |
| image_url | optional public HTTPS image, or null to clear |
| negative_prompt | unsupported when non-empty |
Pricing and result
Every Music Router model charges the fixed Music price per audio generation; the catalog lists each model's provider list price for reference. Read the audio from result.artifacts[] where type is audio. Check the licence terms of any music you publish, and name vocals or lyrics only when you want them.
Sources
Related posts
More in Media tools
- How many audio tracks can one Instagram Reel hold? Up to 20
Meta says you can add up to 20 tracks to a single Reel. How to plan a multi-track sound bed ahead of time and build it in one Sume Timeline render.
- How-to Reel: burn numbered step captions with authored cues
A 45-second tutorial Reel with Step 1 to Step 5 on screen: pass authored cues to Sume video captions, skip speech-to-text, and pay $0.20 for up to 60 seconds.
- ImageKit video smart crop fo-face vs a Sume 9:16 reframe
ImageKit can track faces with fo-face when cropping video. Sume has no subject tracking: you choose a static crop, a fit mode, or one crop per shot.
- imgix bg-remove skips transparent images; Sume RMBG flattens to gray
imgix bg-remove=true skips images that already have transparency and serves the origin on failure. Sume RMBG flattens transparent inputs onto #808080 first.
Written by Sume