Turn a Short into podcast audio with audio detach for $0.01
Audio detach extracts the sound of a hosted video into a wav or mp3 for $0.01 per job. Use it to turn a clip of up to 3 minutes into a podcast cut.

If your Short has a voice track worth hearing without the picture, extract it with Sume's audio detach. It returns a new audio file from one hosted video for $0.01 per job, and the video is untouched. Set format to mp3 if you want a podcast-ready file; the default is wav.
YouTube's help page, read on 2026-10-04, says Shorts can now run up to three minutes. That is long enough for a short audio episode, and it is well inside the detach limits.
How it works
The audio detach docs say the job takes one workspace media.sume.com video, so import the file first. Send video_url and an Idempotency-Key. The result contains audio_url, duration_seconds, format and channels. A whole track longer than 900 seconds needs a range, but a three-minute clip never reaches that.
| Field | Use | Note |
|---|---|---|
| video_url | Required | Workspace media.sume.com video |
| format | wav (default) or mp3 | mp3 for sharing |
| range | Optional | Needed above 900 s |
Make it a real episode
A raw detach keeps whatever is in the Short, including music under the voice. Add a spoken intro, such as a generated voice line, and join the parts with timeline audio concat at $0.01 per job. Total: $0.02 for a two-part episode.
Only use audio you have the rights to. If the Short contains licensed music, a podcast feed is a different use.
Sources
Related posts
More in Use cases
- Tutor intro video: approve the first frame, then pick the tier
A tutor can approve an avatar intro's first frame before paying for the full render, then choose standard, plus or max at generate-video without a new preview.
- 2-second YouTube intro sting: Wan 3.0 has the lowest floor
The shortest clip length Sume's docs list for the Video Router is 2 seconds on wan-3.0. Seedance 2.5 starts at 4. Here is a request and how to trim for less.
- UGC-style ad on Sume: a Format run or the avatar endpoint
Two ways to make a UGC-style ad on Sume: a catalog Format run for a full cut, or the avatar talking-video endpoint for a 4 to 60 second presenter clip.
- UGC-style holiday gift ad from one product photo for $5.16
A 20-second talking-avatar gift ad with your product in frame costs $5.16 on plus and $3.88 on standard. Here is the brief, the settings and the budget.
Written by Sume