Factorsynth is a unique tool for sound deconstruction. It breaks down audio samples into a set of elements using a machine learning algorithm. The pieces are ready for you to rearrange and remix in infinite ways to create complex textures, rhythmic and melodic variations, hybrid sounds and a full new range of sonic transformations!
First released in 2018 as a Max For Live device, version 3 brings the Factorsynth technology to all VST/AU compatible DAWs. For the first time, it also runs as a standalone application.
isolate and remix elements
create hybrid sounds with cross-synthesis
create complex textures
deconstruct and randomize
generate rhythm and melody variations
play components via MIDI
use a matrix controller
draw to modify components
Factorsynth is a powerful software tool that analyzes and decomposes (“factorizes”) audio clips into a set of temporal and spectral components. Once the components are extracted, you can manipulate and recombine them to generate melodic, rhythmic and timbral variations, create hybrid sounds by combining components of two different sounds, use it as a MIDI instrument, or sync it with the DAW host for live remixing.
For more about the technical details and capabilites of Factorsynth, check out this blog post.
Factorsynth is not a stem separator. It is not intended to unmix full instruments (voice, drums…), but to discover and extract unpredictable but interesting sound elements with a certain degree of structure (notes, drum hits, rhythmical or melodic motifs). Please try out the demo to get an idea of the decompositions Factorsynth can produce.
There is no limit on the length of the input sound files, but keep in mind that if you use long files (several minutes) with many components, memory consumption can quickly escalate! Factorsynth works best with short clips (less than 30 seconds), although it is up to you to see how far you can go!
v. 3.1 (Nov 13, 2023)