Last updated: May 13, 2026

May 13 – May 19

Ensemble mode restored with the latest UVR model roster

  • Fixed Ensemble mode submissions so selected strategies can create jobs without requiring a separate model field.
  • Aligned Ensemble strategy values with the processing backend, including Best SDR, Fullness, and Bleedless modes.
  • Updated the scene model roster with the latest UVR defaults and new options such as Gabox FV, Lazy Bat, Aspiration, and Denoise Aggressive models.
  • Improved model selector resilience so newly synced models remain visible even when a localized description has not yet been translated.

Mar 17 – Mar 23

Added two BS-RoFormer models with complete frontend support

  • 🎤 New vocal model: Added BS Roformer Mag Anvuew to Extract Vocals for better magnitude-spectrum accuracy and vocal clarity.
  • 🧼 New dereverb model: Added BS Roformer Dereverb Anvuew to Dereverb for cleaner noreverb output.
  • 🌐 i18n update: Added localized model names and descriptions for consistent multilingual display.
  • 🧩 Frontend sync: Updated model config and output stem typing so both models can be selected and submitted normally.