Which Sume video clips carry audio for the Shorts editor split
YouTube Shorts now separates audio and video tracks. Which Sume video models return sound, which can mute, and what a $0.01 detach adds.
The YouTube Shorts editor is reported to separate audio and video tracks (reported by HeyOrca, read 2026-10-07). Before you rely on that split for a generated clip, check whether the clip has a track to separate. On Sume that depends on the model.
Audio by model
Prices are Sume billable rates (provider list x 1.25, rounded up to the cent per job), read 2026-10-07.
| Model | Audio on the clip | Audio price line |
|---|---|---|
| Wan 3.0 | generate_audio, default true | none |
| MiniMax H3 and H3 Max | native stereo, always on | none |
| Gemini Omni Flash 1.1 | native, always on | none |
| Kling 3 | on or off | $0.14 off, $0.21 on per second |
| Grok Imagine Video 1.5 | silent | none |
Practical pick
Audio detach splits a clip that does have sound into a file you can edit separately. It costs $0.01 per job, needs a media.sume.com video and an Idempotency-Key, and writes wav by default (mp3 is 128 kbps). Detach on a silent Grok clip has nothing to extract, so plan for that case with the error post linked below.
A 10-second Kling 3 clip is $1.40 with audio off and $2.10 with audio on. For the other models the sound is in the price already.
- Need a clean split with separate music later: generate on H3 or Wan, detach for $0.01.
- Need silence from the start: Kling 3 with audio off, or Grok Imagine Video 1.5 for image-to-video.
- Not sure: read the live catalog before you pay.
Sources
Related posts
More in Models
- Which Sume video models take a source video_url? Edit, transfer
Only three Video Router rows accept a video_url source: gemini-omni-flash-1.1 (edit), higgsfield-genjutsu (motion transfer) and h3-max-recast (person swap).
- Which Sume video models take 30 seconds: four ids in the catalog
Four ids in Sume's video catalog reach 30 seconds: seedance-2.5, wan-3.0, higgsfield-genjutsu and h3-max-recast. Which make a clip from a prompt.
- Which AI video models take an audio file as a reference on Sume?
MiniMax H3 and H3 Max, Wan 3.0 and the Seedance 2.x rows accept audio references on Sume; Omni and Kling do not. H3 limits: 3 clips, 2-15 s each, 15 s total.
- Which Sume video models accept an audio reference (audio_url)?
Seedance 2.x, Wan 3.0, MiniMax H3 and H3 Max take audio and video references on Sume. Gemini Omni Flash 1.1 and Recast do not. Rates and limits.
Written by Sume