Factorsynth is a powerful Max for Live device that uses machine learning to decompose any audio clip into a set of elements. You can rearrange and modify these elements to remix clips, remove notes, randomize patterns, create complex textures...

Requirements: Ableton Live with Max For Live, Mac/Windows


Factormini is an introductory version of Factorsynth. It contains Factorsynth's essential features, and uses the same decomposition engine. Factorize your clips with up to 8 components, remix and recombine them in session or arrangement view, randomize the component generation and export the components separately to wave files for further editing.

Requirements: Ableton Live with Max For Live, Mac/Windows


Here you can find old experimental versions of Factorsynth for Max and command-line (both Mac OS only). These versions are not real-time capable and a bit unstable, but you can get a taste of what matrix factorization sounds like.

Requirements: Max (Mac OS only)


C.L.E.E.S.E. (Combinatorial Expressive Speech Engine) is an open-source Python toolbox for performing random or deterministic pitch, timescale, filtering and gain transformations on an input sound. Developed in collaboration with the CREAM team at IRCAM, it has been used to generate sounds for experiments studying how social judgements are conveyed in speech.

  Find it on GitHub