Deepfake detectionVoice: speakers and sound

AntiDeepfake (NII)

Seven speech encoders (wav2vec 2.0, XLS-R, MMS, HuBERT) post-trained to tell live speech from synthetic. The authors note themselves that quality depends heavily on the dataset; a human reviews the output.

Developer: National Institute of Informatics, Yamagishi Lab, Japan
First release: May 2025
Latest release: Oct 2025
Sizes: 0,3B – 2B
License: Non-commercial onlyCC BY-NC-SA 4.0 - research and education, commercial use prohibited
Running: On your own serverAlso runs without a GPU
Industries: Security, Finance, Media and production, Science and research

Deploy on your server Hugging Face

What it does

Checking audio recordings for synthesis
Fine-tuning for your own language and recording channel
Comparing several encoders on your own data
Research into detection robustness

Where it is used

Information securityBanks and insuranceMedia and fact-checkingScience

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

Oct 2025Обновление карточек и весов
May 2025MMS-300M, MMS-1B, HuBERT-XL
May 2025XLS-R-1B и XLS-R-2B
May 2025wav2vec-small и wav2vec-large anti-deepfake

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 AntiDeepfake (NII) be used in a commercial project?

No. License: CC BY-NC-SA 4.0 - research and education, commercial use prohibited. A commercial product needs a different model or a separate agreement with the rights holder.

What hardware does AntiDeepfake (NII) 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 AntiDeepfake (NII) support Russian?

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

Where can I download AntiDeepfake (NII) and what does it cost?

The AntiDeepfake (NII) 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

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

The baseline open model against voice spoofing: it listens to the raw recording and tells a live person from synthesis or a replay. It errs in both directions - its output is a reason for a human to check, not proof.

Details Deepfake detectionSSL Anti-spoofing (wav2vec 2.0 + AASIST)EURECOM · FranceCommercial use allowed

A step beyond AASIST: instead of raw audio it uses the wav2vec 2.0 speech encoder, which helps it hold up on unfamiliar synthesis methods. It errs in both directions - a human reviews the result.

Details Voice: speakers and soundWeSpeakerWeNet community · ChinaCommercial use allowed

A set of ready-made voiceprint models: checks whether the same person speaks in two recordings and helps split a recording by speaker. One of the models is built into pyannote 3.x.

Details

Source: huggingface.co/nii-yamagishilab/wav2vec-large-anti-deepfake. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.