Voice: speakers and soundMusic and sound

Demucs

A classic model that splits a track into vocals, drums, bass and the rest. The v4 hybrid transformer version remains the benchmark; the project is now maintained by its author in his own repository.

Developer
Meta AI, then Alexandre Défossez, France
First release
Dec 2022
Latest release
Jul 2026
Sizes
tens of millions of parameters
License
Commercial use allowedMIT
Running
On your own serverAlso runs without a GPU
Industries
Media and production
Deploy on your server GitHub

What it does

  • Separating vocals from music in a recording
  • Backing tracks and karaoke stems
  • Cleaning speech in videos with background music

Where it is used

Media and productionMusic servicesKaraoke and entertainment

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Demucs 4.1.0
  2. Demucs 4.0.1
  3. Demucs v4 (Hybrid Transformer)

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can Demucs be used in a commercial project?

Yes. License: MIT. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Demucs need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Demucs support Russian?

Language does not matter for this model: it does not work with text.

Where can I download Demucs and what does it cost?

The Demucs weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Comparisons

Similar models

Voice: speakers and soundUVR / MDX-Net / RoFormer (разделение звука)Community: Ultimate Vocal Remover (Anjok07), ZFTurbo, MVSep · International communityCommercial use with conditions

A large open collection of models for separating vocals from music and noise: MDX-Net, BS-RoFormer, Mel-RoFormer, SCNet. The quality leaders for vocals among open solutions.

DetailsVoice: speakers and soundSAM AudioMeta · USACommercial use with conditions

A model that cuts the sound you need out of a recording based on a text description, a mark on the video or a time range: a voice, an instrument, noise. Weights are available on request.

DetailsVoice: speakers and soundClearerVoice (MossFormer)Alibaba (Tongyi Lab) · ChinaCommercial use allowed

Alibaba's set of speech cleanup models: noise suppression, separating overlapping voices, upscaling audio to 48 kHz, and isolating a voice using video of the speaker's face.

Details

Source: pypi.org/project/demucs/. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.