DeepFilterNet vs Kleervox

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.

Kleervox reduces background noise and speaker echo during calls using real-time processing on the device. Its neural noise cancellation separates speech from sounds such as keyboards, traffic, fans, and chatter, while echo cancellation reduces a caller’s voice leaking from speakers back into the microphone. It works as a virtual microphone in apps that let users select a microphone, including Zoom, Google Meet, Microsoft Teams, Discord, Slack, and OBS. The maker says microphone audio, recordings, and cleaned output are not uploaded, stored, or inspected. Its privacy policy also lists collection of Google sign-in details, usage metrics, installer activity, account state, sign-in history, website and demo analytics, and limited billing data. Free provides one hour of cancellation per day; afterward the microphone works without cancellation until local midnight. New accounts receive a seven-day Pro trial after first successful desktop use, with no card required. Downloads are available for Windows 10, Windows 11, and Linux; macOS is described as coming soon. Windows setup uses VB-CABLE, while Linux creates the virtual microphone automatically.