pymss-project/pymss-studio

What it solves

Pymss Studio provides a user-friendly desktop interface for music source separation, removing the need for users to interact with command-line tools. It allows producers and researchers to manage AI models, process audio files in batches, and edit separated audio stems within a single workspace.

How it works

The application acts as a polished wrapper around the pymss core engine. It uses a Vue 3 and TypeScript frontend for the user interface, which communicates via Tauri v2 (Rust) to a Python worker. This worker then executes the actual source separation algorithms and model management tasks provided by the the pymss package.

Who it’s for

It is designed for music producers, audio researchers, and power users who need a professional desktop environment for separating audio tracks into stems.

Highlights

• Workspace Dashboard: Monitors runtime health, active jobs, and local model status.
• Task Queue: Manages batch jobs with stage-level progress tracking, logs, and retry capabilities.
• Model Library: Handles downloading, resuming, and managing storage for separation models.
• Stem Editor: Includes waveform previews, transport controls, and mix controls for reviewing and exporting results.
• Cross-Platform Support: Available for Windows (CUDA/CPU/ROCm), macOS (MLX), and Linux.