Voice: speakers and soundMusic and sound

SAM Audio

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.

Developer
Meta, USA
First release
Dec 2025
Latest release
Dec 2025
Sizes
small, base, large (5 to 15 GB of weights)
License
Commercial use with conditionsSAM License: commercial use allowed, with sanctions and military restrictions; access on request via HF
Running
On your own serverNeeds a GPU
Industries
Media and production
Deploy on your server Hugging Face GitHub

What it does

  • Isolating one person's voice from a noisy recording
  • Removing unwanted sound from a video
  • Splitting a recording into separate sound sources

Where it is used

Media and productionVideo shooting and editingTranscription services

Hardware requirements

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

Versions

  1. SAM Audio (small, base, large)

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.Hugging Face
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 SAM Audio be used in a commercial project?

With conditions. License: SAM License: commercial use allowed, with sanctions and military restrictions; access on request via HF. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does SAM Audio need?

At minimum: One GPU with 16–80 GB — mid-size versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does SAM Audio support Russian?

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

Where can I download SAM Audio and what does it cost?

The SAM Audio 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.

Similar models

Voice: speakers and soundDemucsMeta AI, then Alexandre Défossez · FranceCommercial use allowed

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.

DetailsVoice: 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.

DetailsComputer visionSegment Anything (SAM)Meta · USACommercial use with conditions

Selects any object in photos and videos with a click or a box. The basis for background removal and object counting.

Details

Source: huggingface.co/api/models/facebook/sam-audio-large. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.