Studio-quality voice, without the studio

On-device machine learning strips background noise from speech, so podcasts, voiceovers and audiobooks sound studio-clean on Mac, Windows and Linux.

Pay what you can

Limited time

A launch offer, for a limited time.

Every tool is free for personal use, up to 20 files a week. A license adds commercial use and removes the limit.

Price in US dollars

Taxes calculated at checkout. How licenses work

Docs GitHub RSS

By Nadeem Siddique

PrivacyTerms

Download Ampliflare Audio

Version 1.0.0 · Oct 2, 2026

Windows

macOS

Linux

Run this in a terminal to install it for your user:

curl -fsSL https://static.purplecandy.dev/ampliflare-audio/releases/latest/download/install.sh | bash

Or download a file below and install it by hand.

Windows packages are not code-signed yet, so SmartScreen will ask you to confirm: More info, then Run anyway. Every file has a checksum in SHA256SUMS.

Hear the difference

0:00 / 0:20
20 seconds of speech recorded over loud background noise. Press play, then switch while it plays.

Ampliflare Audio gives your recordings the sound of a treated studio. A deep learning model trained on speech separates your voice from fans, hum, traffic and room noise, right on your computer. Then level, trim and convert the result, in batches. Your originals are never changed.

Five tools

  • Remove noise cleans up speech in one pass. A Strength slider keeps more of the original room sound when you want it.
  • Enhance evens out loudness to the level each place expects: music streaming, podcasts, audiobooks or broadcast. It drops low rumble too.
  • Cut keeps only the part you mark, and Split breaks one recording into pieces. Both show a picture of the sound, so the pauses are easy to find.
  • Convert changes the format: mp3, wav, m4a, flac, ogg or opus.

Made for batches

  • Drop in a whole session and run a tool on every file at once.
  • Save results next to the originals or in one folder, and name them your way, like interview-clean.wav.

Yours, and private

  • Everything runs on your computer. Nothing is uploaded, and it works offline.
  • Pick a macOS or GNOME style, light, dim or dark colours, and an accent.

What people say

Most tools price out independent creators with crazy monthly fees. Getting powerful audio cleaning, noise sliders, and split/cut tools that run 100% privately on my own computer is a massive win.

CemeteriesMusician

Saving around four times what I used to pay for Hush. Handling my weekly batch of episodes locally on my Mac offline is a huge upgrade.

ScottPodcast Editor

1.0, ready for real work

Ampliflare Audio 1.0 is out for macOS, Windows and Linux. It is free for personal use, and a license, at a price you pick, adds commercial use. Personal and commercial use has the details.

New

  • Choose where results go and how they are named, at the bottom of the window.
  • Splitting is easier. The picture shows each part, Split here sits on the playhead, and you can play one part, join two, or split evenly.
  • Pick a macOS or GNOME look, light, dim or dark colours, and an accent.
  • A Help menu links to these docs, and the app has a new icon.

Fixed

  • Windows now finds ffmpeg once it is installed.
  • The title bar follows the colours you pick.
  • Downloads and updates come from a faster, public server.

Every change, with the details behind it, is in the 1.0.0 release notes.

0.1, the first beta

The first beta is out for macOS, Windows and Linux. Drop in your recordings, pick a tool, and get clean files back. Nothing is uploaded: every step runs on your own computer. Getting started is the short tour.

In the box

  • Remove noise, for fans, hum, traffic and room noise under speech.
  • Enhance, which evens out loudness for podcasts, music, audiobooks or broadcast, and drops low rumble.
  • Cut and Split, with a picture of the sound to find the right spot.
  • Convert between mp3, wav, m4a, flac, ogg and opus.
  • Whole batches at once for every tool but Cut and Split.