Skip to main content

A modular synthesizer in pytorch, GPU-optional and differentiable

Project description


The fastest synth in the universe.


torchsynth is based upon traditional modular synthesis written in pytorch. It is GPU-optional and differentiable.

Most synthesizers are fast in terms of latency. torchsynth is fast in terms of throughput. It synthesizes audio 16200x faster than realtime (714MHz) on a single GPU. This is of particular interest to audio ML researchers seeking large training corpora.

Additionally, all synthesized audio is returned with the underlying latent parameters used for generating the corresponding audio. This is useful for multi-modal training regimes.


pip3 install torchsynth

Note that torchsynth requires PyTorch version 1.8 or greater.


If you'd like to hear torchsynth, check out synth1K1, a dataset of 1024 4-second sounds rendered from the Voice synthesizer, or listen on SoundCloud.


If you use this work in your research, please cite:

	title        = {One Billion Audio Sounds from {GPU}-enabled Modular Synthesis},
	author       = {Joseph Turian and Jordie Shier and George Tzanetakis and Kirk McNally and Max Henry},
	year         = 2021,
	month        = Sep,
	booktitle    = {Proceedings of the 23rd International Conference on Digital Audio Effects (DAFx2020)},
	location     = {Vienna, Austria}

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

torchsynth-1.0.2.tar.gz (34.9 kB view hashes)

Uploaded source

Built Distribution

torchsynth-1.0.2-py3-none-any.whl (36.1 kB view hashes)

Uploaded py3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page