Audioseal

Closed weights Facebook AI Research June 2024

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
Facebook AI Research
Organisation type
Industry
Country
United States of America, France
Published
6 June 2024
Authors
Robin San Roman, Pierre Fernandez, Alexandre Défossez, Teddy Furon, Tuan Tran, Hady Elsahar

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Audio, Speech
Task
Audio classification, Audio generation

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Training data
tokens

4,500 hours * 13,680 English words per hour = 61560000 words

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Training code
Open source

The code in this repository is released under the MIT license https://github.com/facebookresearch/audioseal training code: https://github.com/facebookresearch/audioseal/blob/main/docs/TRAINING.md looks like training scripts are in this repo: https://github.com/facebookresearch/audiocraft/blob/main/audiocraft/solvers/watermark.py

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Confident

Sources

Where this record came from and when it was last checked.

Reference
Proactive Detection of Voice Cloning with Localized Watermarking
Last updated
28 November 2025

What the numbers mean

Where it came from

Audioseal was published by Facebook AI Research, in the country recorded as United States of America, during June 2024. It comes out of an organisation categorised as industry.

It works in the domain of Audio, Speech, and is recorded as performing the task of audio classification, Audio generation.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

Answers

Audioseal — common questions

01

Audioseal— what GPU do I need to run it?

None. This is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

02

Audioseal— is it open source?

The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

03

Audioseal— how many parameters does it have?

No parameter count has been published for it, which is why no memory or speed figure appears on this page.

04

Audioseal— who created it?

It was published by Facebook AI Research, based in United States of America, an organisation categorised as industry.

05

Audioseal— when was it released?

It was published in June 2024. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

06

Audioseal— what is it used for?

It works in the domain of Audio, Speech, and is recorded as handling the task of audio classification, Audio generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

Source

Original publication

Record last updated 28 November 2025

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.