Skip to content
SPECIFICTION
Get listed

DeepFilterNet vs Noise Blocker

DeepFilterNet

github.com

Noise Blocker

closedlooplabs.com

Side by side

FigureDeepFilterNetNoise Blocker
Price fromFreeFree
Free planYesYes
Free trial—Yes
Open sourceYes—
WindowsYesYes
macOSYes—
LinuxYes—
APIYes—
Self-hostedYes—
Plans published25
Spec score · AI Noise Cancellation Software9.0 (#1)7.9 (#7)
Spec score · Noise Cancellation Software8.9 (#4)7.9 (#6)
LatencyThe LADSPA plugin has a minimum latency of 20 ms from STFT processing, plus latency from the LADSPA host.The FAQ says audio processing adds about 80 milliseconds of latency, varying by system.
PurposeDeepFilterNet is a low-complexity speech enhancement framework for full-band 48 kHz audio using deep filtering.Noise Blocker removes microphone background sounds such as fans, keyboards, clicks, hiss, and room noise in real time.

Plans

DeepFilterNet

  • DeepFilterNetFree
  • Free and open sourceFree

DeepFilterNet pricing →

Noise Blocker

  • Business trialFree
  • Free versionFree
  • Personal license renewal$30, paid once
  • Personal license$50, paid once
  • Business licensePrice not published

Noise Blocker pricing →

In their own words

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

Noise Blocker

Noise Blocker is a Windows app that reduces unwanted microphone sounds in real time, including fan noise, keyboard sounds, clicks, hiss, and room noise. Version 3 uses AI to distinguish a speaker’s voice from background sound and is designed for everyday laptops. The maker says the app needs no tuning or complicated setup. It is listed as compatible with Zoom, Google Meet, Discord, Slack, Teams, and OBS, and supports microphone audio for recording and streaming. Noise Blocker supports Windows 10 and Windows 11; other operating systems are not currently supported. Processing adds about 80 milliseconds of latency, which varies by system. The free version provides 30 minutes of blocking per week without an email requirement. A Personal license is a one-time payment of $50 for one person on up to three PCs, with 12 months of updates and priority support, indefinite use of covered versions, and a 14-day money-back guarantee. A 30-day business trial for up to 20 employees or computers requires a request and approval; no card is required.

Visit closedlooplabs.com