Hey PH! 👋 I built this because every silence-removal tool I found either required uploading your raw podcast audio to a server (privacy concern + waiting for uploads/downloads) or was locked behind a $20+/mo subscription for a task that's fundamentally pretty simple: cut the dead air. So I built the whole detection + editing pipeline to run client-side using WebAssembly and the Web Audio API — your audio never leaves your browser, there's no file size cap since it's bound only by your device's RAM, and it's instant since there's no upload/download round trip. The tricky part was getting the automatic detection to not clip natural speech — soft consonants and breath releases were getting cut in early versions. I ended up building adjustable safety padding (150–250ms) around every detected cut, plus a waveform view zoomed up to 300x so you can manually verify and fine-tune every cut before exporting. Would love feedback — especially from anyone who edits podcasts regularly. What threshold/padding defaults would be most useful as presets?

Voxora Silence Remover

Remove dead air from podcasts, 100% in your browser

Remove dead air from podcasts, 100% in your browser