RNNoise

Spec sheet

Purpose

RNNoise is a noise suppression library based on a recurrent neural network.Read 4 Oct 2026 · github.com

Security

The opened project pages state a software license but do not describe security certifications or compliance.Read 4 Oct 2026 · github.com

Support

Xiph directs people to its mailing lists or IRC channels for contacting the foundation and community.Read 4 Oct 2026 · xiph.org

License

The repository identifies its license as BSD-3-Clause.Read 4 Oct 2026 · github.com

Build

The README gives an autotools build sequence using autogen.sh, configure, and make.Read 4 Oct 2026 · github.com

CPU optimization

The project recommends AVX2 and describes AVX2 or SSE4.1 runtime CPU detection as build options.Read 4 Oct 2026 · github.com

Distribution

The README says the GitHub repository is a convenience copy and identifies GitLab as the location of the latest source.Read 4 Oct 2026 · github.com

Input format

The demo processes mono 16-bit raw PCM at 48 kHz and its input and output are raw files, not WAV.Read 4 Oct 2026 · github.com

Models

RNNoise can use its included default model or load a custom model from a file, filename, or memory buffer through its API.Read 4 Oct 2026 · github.com

Smaller model

The README describes an alternative little model with increased sparsity.Read 4 Oct 2026 · github.com

Training

Model training requires clean speech and noise data sampled at 48 kHz in 16-bit PCM format.Read 4 Oct 2026 · github.com

Use

The project is intended to be used as a library and includes a command-line demo.Read 4 Oct 2026 · github.com

Plans and prices

Every RNNoise plan and price →

Where Specifiction places it

• AI Noise Cancellation Software#18 of 247.1