Skip to the content
Know your tech before you buy it. Makers: get listed from $49/mo

Pymss

pymss.net

  • Free plan
  • Open source
  • Windows
  • macOS
  • Linux
  • Web
  • iPhone and iPad
  • Android
  • API
  • Self-hosted
8.6 Club score Visit pymss.net

What Pymss is

Pymss is a free, open-source music source separation toolchain that runs on the user's machine and separates audio into vocals, drums, bass, and other stems. Its Studio desktop workspace handles model management, batch jobs, and stem editing. Users can import files or folders, choose a downloaded model, set inference options, and queue processing. Studio can browse, download, resume, and remove model files, with storage cleanup controls. For working with results, it offers waveform previews, mix controls, project persistence, and stem export. Pymss can chain models so each processing step uses the previous step's output. The inference package lists WAV, FLAC, MP3, M4A, AAC, Opus, Vorbis, and Ogg as supported output formats. The project also provides ComfyUI custom nodes, a VST3 ARA plugin for compatible DAWs, and a browser interface bundled with its server. The ARA plugin includes per-stem mute and solo controls; its README names Reaper and Studio One as example hosts. Each repository has its own license, and the Studio README warns that the app is early in development and breaking changes may occur between versions.

Who it suits

Pymss suits people who want to separate audio into stems locally, including users who need batch processing or editing controls. Its ARA plugin may also suit users of compatible DAWs.

Good to know, and what to watch

  • Runs separation on the user's own machine.
  • Studio supports batch jobs and stem editing.
  • Can chain models into processing workflows.
  • Supports WAV, FLAC, MP3, and other listed formats.
  • ARA plugin provides per-stem mute and solo controls.
  • Studio is at an early development stage.
  • Breaking changes may occur between versions.
  • Each repository ships under its own license.

Pymss

Free

Free plan

Getting started

  1. Open the Pymss website
  2. Install the package or desktop Studio on a supported platform
  3. Download a separation model through Studio
  4. Import audio files or folders
  5. Configure inference and queue a job
  6. Review, mix, and export the stems

Limits to check

The free Pymss plan runs locally and is open source. Studio remains early-stage, and its repositories are distributed under separate licenses, including AGPL-3.0 for Studio and MIT for the inference package.

The verdict

Pymss brings local separation, batch processing, and stem editing together, with additional interfaces for browser and DAW workflows. Its early Studio development status is worth considering before relying on it in a settled workflow.

Questions people ask

Is Pymss free?

Yes. The Pymss plan is free, with a free plan and no free trial.

Which platforms does Pymss support?

Pymss lists Android, API, iOS, Linux, macOS, web, and Windows support.

Can Pymss process batches?

Yes. Studio can import files or folders and queue batch jobs.

What audio formats can it export?

The inference package lists WAV, FLAC, MP3, M4A, AAC, Opus, Vorbis, and Ogg.

Does Pymss work with DAWs?

Yes. It provides a VST3 ARA plugin; Reaper and Studio One are named as example hosts.

Is Pymss open source?

Yes. The project is open source, with Studio listed under AGPL-3.0 and the inference package under MIT.

What the maker publishes

ARA integration
The ARA VST3 plugin separates DAW tracks into stems in a background worker and supports per-stem mute and solo monitoring. source
ARA plugin
The ARA plugin separates tracks inside an ARA-capable DAW and provides per-stem mute and solo controls; its README names Reaper and Studio One as example hosts. source
Audio utilities
Included tools cover conversion, inspection, SDR and SI-SDR evaluation, speech recognition, vocal-to-MIDI, silence slicing and audio merging. source
Browser interface
The WebUI is described as a browser interface bundled with the server and shipped with the pip package. source
CLI
The command line supports inference, workflows, ComfyUI JSON execution, ensembles, model registration and server startup. source
ComfyUI integration
Comfy-MSS provides nodes for catalog, custom-model and VR/UVR separation inside ComfyUI. source
Custom models
Users can import weights and configurations for supported model architectures. source
Development status
The Studio README says the app is at an early stage of feature development and breaking changes may occur between versions. source
Editing and export
Studio provides waveform preview, mix controls, project persistence, and stem export. source
External usage
The RVC project describes its PyMSS integration as providing model cataloging, downloading, audio I/O and ensemble utilities. source
Formats
The inference package lists WAV, FLAC, MP3, M4A, AAC, Opus, Vorbis, and Ogg as supported output formats. source
HTTP API
The optional server extra provides a self-hostable HTTP service with dynamic model loading, catalog browsing, downloads and an optional WebUI. source
Import and batch
Studio can import audio files or folders, select a downloaded model, configure inference, and queue jobs. source
Integrations
The project provides ComfyUI custom nodes and a VST3 ARA plugin for use in DAWs. source
Licensing
The official site says each repository ships under its own license; GitHub lists Studio under AGPL-3.0 and the inference package under MIT. source
Licensing
The main Python package is MIT licensed according to PyPI. source
Limit: Intel Mac
There is no dedicated Intel Mac package; source builds require checking inference dependency compatibility. source
Limit: Linux packaging
The current release workflow does not provide Linux installers. source
Limit: mobile
iOS and Android GPU or NPU support is described as future research, with no mobile application release currently provided. source
Limit: model terms
The project warns that repositories and model weights can have separate licences and usage terms. source
Limit: online preview
The online workspace uses included audio and preset stems, so processing personal audio requires downloading Studio or deploying PyMSS with WebUI. source
Limit: prerelease
The Studio README warns that releases include prereleases and may contain breaking changes. source
Local processing
The official site says separation runs entirely on the user's own machine. source
Local processing
Studio and local PyMSS installations process audio on the user’s device; runtime and model downloads need internet access. source

Checked against the maker's pages on 14 Oct 2026.