# jianchang512/vocal-separate

an extremely simple tool for separating vocals and background music, completely localized for web operation,  using 2stems/4stems/5stems models  这是一个极简的人声和背景音乐分离工具，本地化网页操作，无需连接外网

Repository: https://github.com/jianchang512/vocal-separate
Canonical: https://ross.abutalabs.com/products/vocal-separate
Homepage: https://pyvideotrans.com
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: music-separation, spleeter, vocal-separation, voice-separation
Archived: true
Last push: 2024-11-26T06:47:03+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 70
- inputs: {"age_days": 981, "days_push": 645, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1998, forks 223 (observed 2026-08-28T04:06:03.615171+00:00)

## What it is
A minimal local web-based tool for separating vocals from background music in audio or video files, using Spleeter 2stems/4stems/5stems models that are bundled offline. It runs entirely locally with a browser UI, supports CUDA acceleration, and exposes a simple HTTP API.

## Use cases
- extract vocals from a song for karaoke or remixing
- separate accompaniment from a music video
- split a track into drums, bass, piano, and vocals stems
- process audio/video files offline without uploading to the cloud
- batch-separate audio via a local API

## When to choose
- you need fully offline, local vocal/music separation with no internet
- you want a simple two-click GUI rather than scripting Spleeter yourself
- you have an NVIDIA GPU and want CUDA-accelerated separation

## When to avoid
- you need state-of-the-art separation quality beyond Spleeter models
- you need a headless library to embed in your own Python code rather than a standalone app
- you require non-wav output formats or heavy batch pipelines

## Facets
- artifact type: application
- maturity: active
- function: audio-processing, machine-learning, gui, http-server
- domain: media, machine-learning, self-hosted
- platform: windows, python, cross-platform
- tags: vocal-separation, spleeter, music-source-separation, offline, web-ui, cuda-acceleration, audio, linux, macos

## Member repositories
- jianchang512/vocal-separate (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:03.615171+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:02:12.693091+00:00, confidence not recorded.
  - readme: https://github.com/jianchang512/vocal-separate (fetched 2026-08-28T04:06:03.615171+00:00, sha 940d2b8bebfe)
  - homepage: https://pyvideotrans.com (fetched 2026-08-29T10:42:01.206310+00:00, sha ea83000fc034)
- Data as of 2026-08-30T08:39:29.467469+00:00.