tsurumeso/vocal-remover

Health v2 · maintenance only

Adoption not part of the score

1757 stars · 256 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Python command-line tool that uses deep neural networks to separate vocals from instrumental tracks in songs. It includes pretrained models for inference and scripts to train custom separation models on your own dataset.

Use cases

• remove vocals from a song to make a karaoke track
• extract the instrumental version of a song
• isolate vocals from an audio file
• separate singing voice from background music
• train a custom vocal separation model on my own dataset
• split an mp3 into vocals and instruments

When to choose

• you need offline, local vocal/instrumental separation with a simple CLI
• you want a lightweight PyTorch-based separator with pretrained models
• you want to train your own source separation model on paired audio data

When to avoid

• you need real-time or streaming separation
• you need multi-stem separation (drums, bass, etc.) rather than vocals vs instruments
• you prefer a GUI application over command-line usage

Facets

cli-tool · maturity stable

machine-learning audio-processing deep-learning machine-learning media python cross-platform cli vocal-removal source-separation spectrogram pytorch karaoke audio

Member repositories

For agents

markdown · JSON · MCP: product_card(name="tsurumeso/vocal-remover")