Edits audio vibe filter vs a Sume music prompt (no duration field)
Edits lets you filter audio by vibe like chill or bossy. Sume music takes a text prompt instead, with no duration, seed or temperature parameter to pin.

Edits searches an existing audio library by filter. Sume does not search a library by vibe; you describe the vibe in a text prompt and a track is generated. The request has no seed, temperature, guidance or duration parameter, so everything you want pinned goes into the prompt wording.
Edits is from Instagram's creators blog; Sume behavior is from Music 1.0, read 2026-10-01.
What are the Edits vibe and interest filters?
Instagram says you can find audio by vibes like chill or bossy and by interests like fashion and travel: tap the Audio icon, then use the search filters.
How do I describe a vibe to Sume music?
The docs suggest a scene-specific brief across seven axes: emotion, genre, tempo as a number, key and mode, instruments with texture, an arc with one named moment, and era or production. They call these creative directions, not guaranteed output settings, so verify the audio. Put exclusions in the positive prompt, for example "Instrumental, no vocals". The docs also note Music 1.0 requests now resolve through the Music Router, and new integrations should call POST /v1/music-router/generate.
What can I not set?
| Input | Rule in the docs |
|---|---|
duration, duration_seconds | Do not send; unrecognized and rejected |
negative_prompt | Non-empty values return HTTP 400; omit or send an empty string |
prompt | 1 to 5000 characters |
image_url | Optional public HTTPS image for visual conditioning |
How do I get a specific length?
The docs say length is steered by the prompt, for example by saying "a 2-minute track" or using section markers like [0:00-0:30] Intro: .... For an exact length, see exact length with no duration field.
Sources
Related posts
More in Models
- Kling 4.0 10-bit HDR at 1080p and 4K: what later edits keep
Kling says 4.0 outputs 10-bit HDR at 1080p and 4K. Sume's exact video_trim re-encodes to yuv420p; keyframe trims stream-copy. Verify before you grade.
- Kling 4.0 21:9 ultrawide: check Sume's aspect ratios
Kling 4.0 supports 21:9 output. Sume documents 21:9 as a ratio, but each model lists its own supported_aspect_ratios, so read them before sending.
- Kling 4.0 five reference videos vs Sume's 1 to 3 video URLs
Kling 4.0 takes up to 5 reference videos, 30 seconds combined. Sume lists 1-3 reference_video_urls on the legacy shape and varies per model.
- Kling 4.0 Flash early access: how to tell what Sume lists
Kling 4.0 Flash opened to a limited group on Sept 28 with full launch in October. On Sume, a model is callable when the live catalog lists it.
Written by Sume