YouTube Shorts: Seedance 2.5 audio on, off or detached, same price
Shorts editors now separate audio and video tracks. On Sume a 15-second Seedance 2.5 clip is $8.67 with or without audio; detach the sound for $0.01 per job.

A 15-second 9:16 Seedance 2.5 clip costs $8.67 at 720p on Sume whether generate_audio is true or false. Audio is optional on this model and the estimate has no audio term, so the choice is about the edit, not the bill. If you want the generated sound as its own track, Sume's audio detach job pulls it out of the finished video for $0.01 per job.
The reason this is a live question: the YouTube Shorts editor now separates audio and video tracks, according to a HeyOrca roundup (secondary source, read 2026-10-07). A clip with a silent or separable audio track fits that workflow better than one with sound baked in.
Three ways to handle the sound
| Route | Request | Extra cost | When to use it |
|---|---|---|---|
| Mute the clip | generate_audio: false | $0.00 | You will add music or a voiceover in the editor |
| Keep the sound in the clip | Default (true) | $0.00 | Ambient audio is the point, nothing else is added |
| Keep it, but as a separate file | Default, then audio detach on the finished video | $0.01 per job | You want to trim, duck or replace the sound later |
Detach, step by step
Audio detach takes one video from your workspace (media.sume.com), returns a new audio artifact (wav by default) and leaves the video unchanged. It needs an Idempotency-Key header. The finished video must already be a workspace file; import it first if it lives elsewhere. See the audio detach docs (read 2026-10-07).
curl -X POST "https://api.sume.com/v1/audio-detach" \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: shorts-detach-001" \
-d '{"video_url": "https://media.sume.com/your-workspace-video.mp4"}'Which to choose
Pick generate_audio: false when you already know you will replace the sound. A generated track you throw away is not billed separately here, but it can mislead a review of the first take. Pick the detach route when the generated sound is a starting point.
A 15-second vertical clip fits a Short. Keep each clip near the length of one beat and join them on a timeline rather than asking for 30 seconds of one scene.
Sources
Related posts
More in Media tools
- Shorts editor splits audio from video: make voice and music files
YouTube's Shorts editor now keeps audio apart from video. Make a clean voice file and a music bed on Sume for $0.163 and drop each on its own track.
- YouTube Shorts thumbnail file type and size: JPG or PNG, 9:16, 50 MB
YouTube's help page gives JPG or PNG, 9:16, 2160x3840 and 50 MB on desktop for Shorts thumbnails. Export that from a video frame with Sume video frames.
- YouTube suggests 3 Shorts thumbnail frames: pick from 24 yourself
YouTube suggests three frames for a Shorts thumbnail. Pull up to 24 candidates with Sume video frames and choose your own.
- YouTube thumbnails take JPG or PNG: output formats per Sume image row
YouTube accepts JPG and PNG thumbnails. Sume rows list png, jpeg or webp; Recraft V4 is webp only, Soul and Ideogram 4.5 pick the format for you. Table and fix.
Written by Sume