Fugatto 1

Closed weights NVIDIA 2.5B parameters November 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
NVIDIA
Organisation type
Industry
Country
United States of America
Published
25 November 2024
Authors
Rafael Valle, Rohan Badlani, Zhifeng Kong, Sang-gil Lee, Arushi Goel, Sungwon Kim, Joao Felipe Santos, Shuqi Dai, Siddharth Gururani, Aya AlJa'fari, Alex Liu, Kevin Shih, Wei Ping, Bryan Catanzaro

What it does

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

Domain
Multimodal, Language, Audio
Task
Audio generation
Approach
Supervised
Numerical format
Unknown

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.

Parameters
2.5B
Training data
tokens

"our dataset is comprised of at least 50,000 hours of audio"

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Training hardware
NVIDIA A100
Chips used
32
Power draw
25.2 kW

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.

Weights
Closed — provider access only
Model access
Unreleased
Training code
Unreleased

demos only https://fugatto.github.io/

How it is classified

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

Why it is tracked
SOTA improvement

"We showcase Fugatto’s performance on traditional TTA benchmarks that measure a model’s ability to synthesize general sounds (AudioCAPS) and music (MusicCAPS) that follow instructions provided in text. We use the metrics (FD, FAD, and IS) and data splits (train, test) used in Kong et al. (2024b). Results in Table 3a and Table 3b shows that our model achieves strictly better scores than existing generalist models, while occasionally outperforming expert models"

Record confidence
Confident

Sources

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

Reference
Fugatto 1 - Foundational Generative Audio Transformer Opus 1
Last updated
28 November 2025

What the numbers mean

Where it came from

Fugatto 1 was published by NVIDIA, in the country recorded as United States of America, during November 2024. The category the publisher falls under is industry.

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

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

What went into building it

It is tracked in the underlying dataset for one reason in particular: sOTA improvement.

Answers

Fugatto 1 — common questions

01

Fugatto 1— 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

Fugatto 1— is it open source?

No. Its weights have not been published, so it exists only as a service controlled by its owner.

03

Fugatto 1— how many parameters does it have?

It has a parameter count of 2.5B. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.

04

Fugatto 1— who created it?

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

05

Fugatto 1— when was it released?

It was published in November 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

Fugatto 1— what is it used for?

It works in the domain of Multimodal, Language, Audio, and is recorded as handling the task of 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.