PyTorch
demucs
audio-separation
music-source-separation
music-source-separation-model
source-separation
audio-source-separation
stem-separation
music-separation
vocal-separation
vocal-isolation
vocal-removal
vocal-extraction
instrumental-separation
instrumental-extraction
instrumental-isolation
karaoke
karaoke-maker
acapella
acapella-extraction
vocals
voice-isolation
drum-separation
drums-isolation
bass-separation
bass-isolation
guitar-separation
piano-separation
instrument-separation
multi-stem-separation
two-stem-separation
four-stem-separation
six-stem-separation
htdemucs
htdemucs-ft
htdemucs-6s
mdx-extra
hybrid-transformer
transformer
deep-learning
machine-learning
artificial-intelligence
generative-ai
neural-networks
audio-ai
music-ai
music-processing
audio-processing
audio-analysis
digital-signal-processing
dsp
audio-enhancement
audio-extraction
audio-manipulation
audio-conversion
audio-transcription
audio-tools
music-tools
music-production
music-editing
music-remix
remix-tools
audio-effects
audio-export
audio-downloader
mp3
wav
flac
mp4
mkv
mov
ffmpeg
media-processing
video-audio-extraction
video-to-audio
video-processing
multimedia
audio-file-converter
bitrate-control
volume-boost
batch-processing
zip-download
google-colab
colab-notebook
jupyter-notebook
google-colab-gpu
nvidia-t4
gpu-acceleration
cuda
cloud-gpu
python
python-project
model-inference
inference
open-source-ai
ai-tools
audio-separation-tool
vocal-remover-tool
music-separation-tool
audio-separation-tutorial
tutorial
beginner-friendly
no-code
low-code
interactive-ui
ipywidgets
ai-workflow
machine-learning-project
ai-project
πΆ Demucs in Google Colab: Free Vocal & Stem Separation
This repository contains an easy-to-use Google Colab notebook for running Demucs. This AI tool allows you to isolate vocals, drums, bass, and other instruments from any audio or video file for free using a Google Colab T4 GPU.
π₯ Watch the Tutorial: Setup Demucs in Google Colab
π Run in Colab: Open Google Colab Notebook
β¨ Features Supported in this Notebook
This notebook makes it incredibly simple to use Demucs through an interactive UI:
- Media Support: Upload audio (
.mp3,.wav,.flac, etc.) or video files (.mp4,.mkv,.mov, etc.) directly. The tool automatically extracts the audio track from videos. - Multiple Models: Choose between
htdemucs,htdemucs_ft,htdemucs_6s, andmdx_extra. - Separation Modes: Extract 2 stems (e.g., Vocals + Instrumental), 4 stems, or up to 6 stems (Vocals, Drums, Bass, Other, Guitar, Piano).
- Audio Output Settings: Export as
mp3,wav, orflacwith adjustable bitrates. - Volume Boost: A built-in slider (0-20 dB) allows you to automatically boost quiet background/instrumental tracks.
- Automatic Zipping: Packages all your separated stems into a
.zipfile and downloads it automatically.
π οΈ How to Use
- Click the "Open in Colab" badge above.
- Go to Runtime > Change runtime type and ensure a T4 GPU is selected.
- Step 1: Click the play button on Cell 1 to install Demucs, set up FFmpeg, and check your GPU status.
- Step 2: Scroll to Cell 2 and choose your settings (Model, Separation Mode, Output Format, etc.).
- Click the play button on Cell 2. A button will appear asking you to upload your files.
- The AI will extract the audio, separate the stems, and display audio players so you can preview the results immediately! Finally, it will automatically download your tracks in a ZIP file.
π€ Credits
- Tutorial & Notebook Creator: @CoinNoin
- Underlying AI Model: Facebook Research / Demucs
Inference Providers NEW
This model isn't deployed by any Inference Provider. π Ask for provider support