[e925]

fast-asd (Sieve)★★★★★

🆓 free🐍 sidecar

Tells your video which person is actually talking. Powers auto-cropping for clips.

why it matters

If you want to take a multi-person podcast and auto-crop it to the vertical 9:16 format TikTok and Reels want, the video needs to know WHO is talking at any given second. fast-asd figures that out — audio + lip movement detection — so your crop follows the active speaker.

Stale repo (last updated mid-2024) but still works, and the pattern is still how every podcast clipper does speaker tracking under the hood. Python sidecar, MIT, free.

install

git clone https://github.com/sieve-community/fast-asd

where to find it

repo health82
possibly unmaintained

no commits in 1 year. this doesn't mean it's broken — some small repos are "finished" — but if you hit an install issue, it may not get patched quickly.

avoid if

You aren't building your own video pipeline. Most creators should just pay OpusClip and skip the plumbing.

see it in action
open the module that demos fast-asd (Sieve)

tags

more in video & clipping

last reviewed · 2026-04-22 · added 2026-04-22