Hear it first
Real separation output from VoxSplit. Listen to the original, then the extracted stems — same 30-second clip, no touch-ups.
Loading demo…
Why local-first?
Your music never leaves your machine. No upload queues, no per-minute fees, no expiry links — just a FastAPI service and your GPU doing the work. Batch a whole album while you make coffee.
Run it yourself
From PyPI (Python 3.10+, weights download on first use):
pip install voxsplit voxsplit
Using uv? uv tool install voxsplit. NVIDIA Linux box? See the repo's deploy/ for a CUDA Docker build.
From source:
git clone https://github.com/michael-borck/voxsplit cd voxsplit uv venv && uv pip install -e . uvicorn backend.main:app --port 8399
Apple Silicon: RoFormer & Demucs models accelerate via MPS automatically. First model use downloads weights once (~1 GB for RoFormer).
The models
On-demand weights from the UVR / python-audio-separator ecosystem: Mel-Band RoFormer (current SOTA for karaoke/vocals), UVR's MDX-Net line, and Demucs 4-stem — all selected per job from the web UI.