pymss-project/pymss-studio

Cross-platform desktop GUI for music source separation

What it is

Pymss Studio is a cross-platform desktop application that brings music source separation to a local GUI. It sits on top of the pymss engine, letting users break audio into stems (vocals, instruments, drums, etc.), edit them, and export mixes — all on their own machine.

Core capabilities

  • Source separation with model ensembles, batch processing, device/format/one-key export options
  • A model library with search, download progress, favorites, notes, and storage management; supports importing custom weights
  • Task queue with progress logs, cancel/retry, and session organization
  • Stem editor: multitrack waveforms, clips, volume/pan, mute/solo, fades, effects, recording, and project persistence
  • Audio tools: format conversion, FFprobe inspection, SDR/SI-SDR evaluation, ASR via FunASR, vocal-to-MIDI via GAME, silence slicing, and audio merging
  • Workflow editors (simple and node-based) to chain separation, processing, and ensemble steps
  • Runtime management: CPU, CUDA, ROCm, and MLX inference environments auto-configured per platform

How it's built

The app is Tauri 2 (Rust backend) + Vue 3 (TypeScript frontend) with a Python inference worker. Models and audio processing run locally; only model/runtime downloads require network. It bundles a bootstrap Python runtime so users don't need to install Python themselves.

Who it's for

Music producers, audio editors, researchers, and hobbyists who want to separate or clean up audio without sending files to the cloud. Supports Windows (x64), macOS 14+ Apple Silicon, and Linux (from source).

Notes

  • Active development; releases include prereleases.
  • GPU acceleration depends on hardware/drivers/model — fallback to CPU if uncertain.
  • Editor projects reference audio files by path; back up associated audio.
  • Licensed AGPL-3.0.

Verdict

A genuine, substantial AI application: it orchestrates real machine-learning inference (source separation, ASR, vocal-to-MIDI) behind a polished desktop UI, with meaningful engineering (runtime manifests, multi-backend support, workflow automation).

Related

  • Project
    nomadkaraoke/python-audio-separator

    Audio Separator is a Python library/CLI that uses deep‑learning models (MDX‑Net, VR, Demucs, MDXC) to split music files into stems such as vocals, instrumental, drums, etc. It supports CPU, CUDA, Apple Silicon (MPS/CoreML), and experimental DirectML, offers Docker images, and provides a model catalog with filtering options.

  • Project
    SUC-DriverOld/MSST-WebUI

    A web-based interface for Music-Source-Separation-Training that allows users to isolate vocals and instruments from music tracks using various AI models.

  • Project
    Eddycrack864/UVR5-UI

    A user-friendly graphical interface for the python-audio-separator tool that allows users to isolate vocals and instruments from audio and video files using various AI models.

  • Dispatch
    StemDeck Open-Source Local AI Stem Separator

    StemDeck is a free, open‑source desktop app that runs locally to split audio into six stems using Demucs, offering a privacy‑preserving alternative to cloud services.

  • Project
    timoncool/YuE2-Studio

    YuE2 Studio is a standalone Windows application for generating, editing, and training AI music models, providing a complete workflow for creating songs from lyrics and scores without needing Python.