Voice: speakers and sound

DeepFilterNet

Lightweight real-time speech noise suppression that works even on a regular CPU and low-power devices. Removes hum, street and office noise while keeping the voice.

The last open version came out in Aug 2023. The family has not been updated for a long time: the model still works, but do not expect fixes or new sizes.

Developer
Hendrik Schröter (University of Erlangen), Germany
First release
May 2022
Latest release
Aug 2023
Sizes
about 2M
License
Commercial use allowedMIT or Apache 2.0, your choice
Running
On your own serverAlso runs without a GPU
Industries
Customer support, Media and production
Deploy on your server GitHub

What it does

  • Cleaning calls and voice messages of noise
  • Preparing recordings before speech recognition
  • Noise suppression for video calls

Where it is used

Call centersVideo conferencing and telephonyMedia and podcasts

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
no versions
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. v0.5.6
  2. DeepFilterNet3
  3. DeepFilterNet2

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 DeepFilterNet be used in a commercial project?

Yes. License: MIT or Apache 2.0, your choice. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does DeepFilterNet 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 DeepFilterNet support Russian?

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

Where can I download DeepFilterNet and what does it cost?

The DeepFilterNet 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 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.

DetailsVoice: speakers and soundResemble EnhanceResemble AI · USACommercial use allowed

A speech enhancement model: removes noise and restores lost frequencies so a muffled recording sounds studio-quality. Good for preparing a voice for voiceover.

Details

Source: github.com/Rikorose/DeepFilterNet/releases. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.