DeepFilterNet vs neep

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.

neep is computer software that reduces noise and echo during voice and video calls. It processes both the microphone audio you send and the incoming audio you hear. For outgoing sound, it can suppress nearby voices after you register your own voice, along with noises such as barking, keyboard use, fans, and lawn equipment. For incoming sound, it can reduce noise from the other caller’s environment. It also addresses echo caused by a poor microphone or your voice returning through the call. neep works with apps that let you select a microphone; setup guides cover Zoom, Microsoft Teams, Google Meet, Discord, and RingCentral. Processing takes place on your device. The company says its cloud connection is limited to login and licence checks, and that it does not record, store, or share call audio. It runs on Linux, macOS, and Windows; Linux support lists Ubuntu 20.04, Debian 10, or Fedora 37 as minimum versions. Plans start at $9/user/mo billed annually, with a 14-day trial.