@audio/denoise vs PD Cleaner

@audio/denoise is a free web tool for cleaning recordings and listening to or saving the result. It handles targets including steady background noise, mains hum, clicks, pops, vinyl crackle, clipping, wind rumble, plosives, sibilance, room reverb, and noise between phrases. The page describes thirteen open-source restoration methods and a classifier. Automatic mode measures properties of a recording, selects a specialized method, and displays its plan; users can instead choose methods such as dehum, declick, declip, and gate. Audio is processed in the browser, and the page says it is not uploaded or sent off the device. The approach uses classical signal processing rather than AI noise removal. For music, the page identifies hum, clicks, crackle, and clipping as treatable, while advising light use of broadband denoising and comparison with the original. Machine-learning models may perform better on heavy speech-over-noise. The associated npm package processes mono Float32Array audio. Automatic mode does not choose dereverb, which must be selected explicitly.

PD Cleaner is a free Windows app for reducing clicks, crackle, hiss, and hum in old recordings, particularly public-domain recordings made before 1926. Drop in a file and it analyzes its era, noise, and clicks; a Clean dial lets you adjust the cleaning. Its voicings cover cylinders, acoustic 78s, and early electric recordings, alongside an uncoloured transfer option. A live before-and-after spectrum analyzer can show a curve, waterfall, or both, and users can solo noise being removed. The app works as a VST3 insert in a DAW or as a standalone program. Folder-based batch processing with one preset is limited to the standalone version. Built-in formats are WAV, FLAC, AIFF, Ogg, MP3, and Opus; a free optional add-on provides AAC and more. It supports 24-bit archival exports and says it does not overwrite the original file. The maker describes it as offline software. The Windows release is open source under AGPLv3, and its build may show an unknown publisher warning when first run.