DeepFilterNet vs Riverside Magic Audio

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.

Riverside Magic Audio is an audio enhancer and equalizer for improving recordings. Its batch processing removes background noise, echo, and reverb, and adjusts frequency bands, voice clarity, loudness, and volume. Riverside describes it for podcasts, social clips, meetings, interviews, voice recordings, and tutorials. You can upload audio or video in formats including MP3, WAV, OGG, MP4, MPEG, and WEBM. It runs on Android, iOS, macOS, and the web. Riverside says it does not use your data to train the model, and its pricing FAQ says the feature does not require AI credits. Magic Audio is included with Pro, listed at $24 a month billed annually ($288 annually). A free plan is also listed, with a one-off two hours of multi-track recordings, video up to 720p, a Riverside watermark, and 44.1 kHz audio. The pricing note lists a 14-day trial. Separate-track download hours depend on the plan, though recording is unlimited on Pro, Grow, and Webinar.