News for hackers. Stuff that matters.
Re:Show HN: Chipmunkify – I used ML to solve audio's dumbest... by treelover on Sunday April 12, 2026 @11:42PM (#47747313)
You know those YouTube channels with millions of views that are just popular songs, but chipmunk? They sound awful because they pitch-shift the entire track.

I fixed it.

The pipeline: Upload an MP3 -> Demucs isolates the vocals -> Rubber Band pitch-shifts them into the rodent register -> FFmpeg glues it back together. Hosted on Modal.

Guardrails protecting my $5/month Modal budget and net worth:

* 10MB max upload * First 30 seconds only (Demucs is computationally brutal) * 3 requests/IP/day

I delete your files immediately: not out of principle, but because I genuinely cannot afford to store them.

If the site throws an error, you've assassinated my budget and I will pour one out.

Try it out and let me know what you think. I suggest using a song that you love!

Re:Show HN: Chipmunkify – I used ML to solve audio's dumbest... by jnh-12 on Monday April 13, 2026 @07:45AM (#47750646)
honestly very valid problem, and equally valid of a solution. Would invest
Re:Show HN: Chipmunkify – I used ML to solve audio's dumbest... by treelover on Tuesday April 14, 2026 @02:00AM (#47761791)
thx!
Re:Show HN: Chipmunkify – I used ML to solve audio's dumbest... by blemis on Monday April 13, 2026 @05:42PM (#47758193)
love the budget-constraints section, feels way too familiar. i'm running 7 NLP models on an $11/month VPS for a different project and every architecture decision ends up being "what's the cheapest way that doesn't burn my bank account on one runaway request."

question — how are you handling demucs cold starts on modal? cold start was what eventually pushed me off modal for a request-response

use case. the user is staring at a spinner for 20-30s on first invocation and it kills conversion. did you solve it or just eat it because the rest is so computationally heavy anyway?