Ian Sampson has introduced a new macOS app that uses artificial intelligence to remove background noise and reverb from recorded speech without audible artifacts or loss of clarity. The Hush app makes it easy to produce clean voiceovers, podcasts, audiobooks, and dialogue, without an isolation booth or professional studio.
Hush builds on the transformer architecture — the technology that powers generative models like ChatGPT and DALL·E 2 — to isolate speech with greater precision and fewer artifacts than previous approaches. It suppresses broadband noise, transient sounds like barking dogs or honking horns, and reflections from untreated rooms.
Hush is also one of the first professional audio tools to run on the Neural Engine, a subprocessor for machine learning on Apple Silicon Macs. The Neural Engine allows Hush to render audio quickly and efficiently, without heating up the computer or spinning up the fans.
Hush is available now on the Mac App Store for an introductory price of $49.99 USD. A 21-day free trial is available at the Hush website.
More information: Hush