Skip to content
SPECIFICTION
Get listed

CrumplePop vs DeepFilterNet

CrumplePop

borisfx.com

DeepFilterNet

github.com

Side by side

FigureCrumplePopDeepFilterNet
Price from$14.58/moFree
Free plan—Yes
Free trial——
Open source—Yes
WindowsYesYes
macOSYesYes
Linux—Yes
API—Yes
Self-hosted—Yes
Plans published32
Spec score · AI Speech Enhancement Software6.6 (#30)8.7 (#5)

Plans

CrumplePop

  • Multi-Host Monthly Subscription$25 a month
  • Multi-Host Annual Subscription$175 a year
  • Perpetual License$345, paid once

CrumplePop pricing →

DeepFilterNet

  • DeepFilterNetFree
  • Free and open sourceFree

DeepFilterNet pricing →

In their own words

CrumplePop

CrumplePop is audio software from Boris FX, headquartered in Boston, Massachusetts, and offered as a plugin for macOS and Windows. Plugin support is listed, with paid plans covering multi-host ARA, VST, AU, and AAX formats. Those plans also include the full CrumplePop toolkit and the SoundApp standalone application. The Multi-Host Monthly Subscription costs $25 a month, billed monthly. The Multi-Host Annual Subscription costs $175 a year, billed annually. A Perpetual License costs 345.00 USD once. A free plan is available, and the product listing includes a 15-day trial. Each paid option specifies the same toolkit, standalone application, and multi-host plugin support, so the listed difference is billing term or one-time licensing. CrumplePop runs on macOS and Windows. Buyers can therefore choose between starting with the free plan, trying the software for 15 days, paying monthly, paying annually, or purchasing a perpetual license.

Visit borisfx.com

DeepFilterNet

DeepFilterNet is a free, open-source framework for speech enhancement on full-band 48 kHz audio, using deep filtering. Its command-line tool suppresses noise in WAV files, with 48 kHz as its only supported sampling rate. A LADSPA plugin provides real-time noise suppression and can be used with PipeWire filter chains to create a virtual microphone or audio output, including for VoIP apps such as Zoom or Discord. The plugin's minimum latency is 20 ms from STFT processing, plus any delay added by the LADSPA host. The Rust command-line tool defaults to DeepFilterNet2; the Python interface documents DeepFilterNet and DeepFilterNet2. An optional post-filter may slightly over-attenuate very noisy sections. The framework supports Linux, macOS and Windows, though training is tested only under Linux. The Python package installs as deepfilternet, and an optional train extra adds data-loading functionality for Linux training. Code is available under either the MIT License or Apache License 2.0.

Visit github.com