Skip to main content

Local vocal removal / audio source separation

Project description

voice-remover

Local vocal removal and audio source separation.

Install

pip install voice-remover

Usage

voice-remover "track.mp3" ./outputs/
voice-remover "track.mp3" ./outputs/ --device cuda
voice-remover "track.mp3" ./outputs/ --device mps

Output files are saved as <track>_no_vocals.mp3 in the specified directory.

Arguments

Argument Description
input_file Path to the input audio file
output_dir Directory where the output MP3 will be saved

Options

Flag Default Description
--device cpu Inference device: cpu, cuda, mps

Requirements

  • Python 3.11–3.14
  • FFmpeg (brew install ffmpeg / apt install ffmpeg)

Model weights download automatically on first run from Hugging Face (felipeinfantino/voice-remover). Cached at ~/.cache/voice-remover/models/.

Development

git clone https://github.com/felipeinfantino/voice-remover
cd voice-remover
poetry install
poetry run voice-remover "track.mp3" ./outputs/

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

voice_remover-0.1.0.tar.gz (7.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

voice_remover-0.1.0-py3-none-any.whl (10.2 kB view details)

Uploaded Python 3

File details

Details for the file voice_remover-0.1.0.tar.gz.

File metadata

  • Download URL: voice_remover-0.1.0.tar.gz
  • Upload date:
  • Size: 7.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/2.3.2 CPython/3.11.14 Darwin/24.3.0

File hashes

Hashes for voice_remover-0.1.0.tar.gz
Algorithm Hash digest
SHA256 fded02725c40f40a9331e83f0759cc517dc367d506eda7445959d284c6d83ddd
MD5 f284c522b02bae8db8f8b39fa6f93ae8
BLAKE2b-256 cb8630bc1d93b7ea6804a30da98d5b4bfa683f31ea4631a497fd5c066e1cd36f

See more details on using hashes here.

File details

Details for the file voice_remover-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: voice_remover-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 10.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/2.3.2 CPython/3.11.14 Darwin/24.3.0

File hashes

Hashes for voice_remover-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 2cc1004ebeca21a0e94f5ec8044d78d1a95998efe579b6201a001f7fa5d1fd0b
MD5 d726c0ec742891bde4d175d2316b3ae6
BLAKE2b-256 e328219ffba8d42184509ee0402b063a911fd74c6753d78cbe882d7eb462938e

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page