Voice: speakers and sound

ClearerVoice (MossFormer)

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.

Developer
Alibaba (Tongyi Lab), China
First release
Nov 2024
Latest release
Aug 2025
Sizes
under 1B
License
Commercial use allowedApache 2.0
Running
On your own serverAlso runs without a GPU
Industries
Customer support, Media and production
Deploy on your server Hugging Face GitHub

What it does

  • Noise suppression in conversation recordings
  • Separating two voices speaking at once
  • Improving old and phone recordings

Where it is used

Call centersMedia and archivesVideo calls

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. Аудиовизуальные модели выделения голоса
  2. MossFormer2 SR 48K
  3. MossFormer2 SE/SS, FRCRN

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 ClearerVoice (MossFormer) be used in a commercial project?

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

What hardware does ClearerVoice (MossFormer) 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 ClearerVoice (MossFormer) support Russian?

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

Where can I download ClearerVoice (MossFormer) and what does it cost?

The ClearerVoice (MossFormer) 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 soundDeepFilterNetHendrik Schröter (University of Erlangen) · GermanyCommercial use allowed

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.

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.

DetailsVoice: 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.

Details

Source: huggingface.co/api/models?author=alibabasglab. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.