Background noise is the fastest way to make a good recording sound cheap: a laptop fan, mains hum, traffic outside, the echo of an untreated room. You can clean most of it up after the fact, on your own computer, without sending the file to a web service.
This guide uses Gleam Audio, which purplecandy makes. It runs a speech-trained model locally, works offline, and is free for personal use (up to 20 files a week).
What you need
- The recording, in a common format: wav, mp3, m4a, flac, ogg, opus, AIFF and many more.
- Gleam Audio for macOS, Windows or Linux. It brings its own ffmpeg, so there is nothing else to install.
1. Install the app
Download the file for your computer from the Gleam Audio page.
- macOS: open the disk image and drag the app to Applications.
- Windows: run the setup file.
- Linux: one command installs it, no sudo needed:
curl -fsSL https://static.gleamaudio.com/gleam-audio/releases/latest/download/install.sh | bash2. Add your recordings
Drop the files on the window, or click Open Files…. You can add a whole session at once; every tool except Cut and Split runs on the full list.
3. Run Remove noise
Pick Remove noise in the sidebar (it’s first). The Strength slider decides how much of the original room sound stays: lower it to keep more of the room.
At the bottom, choose where results go: next to the originals (the default) or a folder you pick. Then click Run. New files get the old name plus what was done, like talk-clean.wav. Your originals are never changed, and a result never overwrites an existing file.
4. Even out the loudness
A clean file can still be too quiet or too loud for where it’s going. Run Enhance on the cleaned files and pick the destination: music streaming, podcasts, audiobooks or broadcast. It sets the loudness each one expects and drops low rumble too. (What “loudness” means here: see LUFS.)
5. Convert for publishing
Most podcast hosts want mp3. Convert writes mp3, wav, m4a, flac, ogg, opus and more.
When it won’t help
- Music: Remove noise is tuned for speech. On music it can take out more than you want, so try a lower Strength.
- Clipping and distortion: noise removal takes noise out; it can’t rebuild a waveform that was clipped while recording.
Takeaways
- Clean speech offline in three steps: Remove noise, Enhance, Convert.
- Keep Strength lower for anything with music in it.
- Fix levels after cleaning, not before, so the noise isn’t boosted along with the voice.