Skip to content
Recurrent neural network for audio noise reduction, slightly improved for general use
C Other
  1. C 98.2%
  2. Other 1.8%
Branch: master
Clone or download
Pull request Compare This branch is 25 commits ahead, 7 commits behind xiph:master.
Fetching latest commit…
Cannot retrieve the latest commit at this time.


RNNoise is a noise suppression library based on a recurrent neural network.
RNNoise-nu is a modified version of RNNoise aimed to be a bit more general

To compile, just type:
% autoreconf -i
% ./configure
% make

% make install

While it is meant to be used as a library, a simple command-line tool is
provided as an example. It operates on RAW 16-bit (machine endian) mono
PCM files sampled at 48 kHz. It can be used as:

./examples/rnnoise_demo <number of channels> <maximum attenuation> [model to use] < input.raw > output.raw

The output is also a 16-bit raw PCM file.

For information on the neural network models available, see
You can’t perform that action at this time.