
A team of generative AI researchers created a Swiss Army knife for sound, one that allows users to control the audio output simply using text.
While some AI models can compose a song or modify a voice, none have the dexterity of the new offering.
Called Fugatto (short for Foundational Generative Audio Transformer Opus 1), it generates or transforms any mix of music, voices and sounds described with prompts using any combination of text and audio files.
For example, it can create a music snippet based on a text prompt, remove or add instruments from an existing song, change the accent or emotion in a voice - even let people produce sounds never heard before.
This thing is wild, said Ido Zmishlany, a multi-platinum producer and songwriter - and cofounder of One Take Audio, a member of the NVIDIA Inception program for cutting-edge startups. Sound is my inspiration. It's what moves me to create music. The idea that I can create entirely new sounds on the fly in the studio is incredible.
A Sound Grasp of Audio We wanted to create a model that understands and generates sound like humans do, said Rafael Valle, a manager of applied audio research at NVIDIA and one of the dozen-plus people behind Fugatto, as well as an orchestral conductor and composer.
Supporting numerous audio generation and transformation tasks, Fugatto is the first foundational generative AI model that showcases emergent properties - capabilities that arise from the interaction of its various trained abilities - and the ability to combine free-form instructions.
Fugatto is our first step toward a future where unsupervised multitask learning in audio synthesis and transformation emerges from data and model scale, Valle said.
A Sample Playlist of Use Cases For example, music producers could use Fugatto to quickly prototype or edit an idea for a song, trying out different styles, voices and instruments. They could also add effects and enhance the overall audio quality of an existing track.
The history of music is also a history of technology. The electric guitar gave the world rock and roll. When the sampler showed up, hip-hop was born, said Zmishlany. With AI, we're writing the next chapter of music. We have a new instrument, a new tool for making music - and that's super exciting.
An ad agency could apply Fugatto to quickly target an existing campaign for multiple regions or situations, applying different accents and emotions to voiceovers.
Language learning tools could be personalized to use any voice a speaker chooses. Imagine an online course spoken in the voice of any family member or friend.
Video game developers could use the model to modify prerecorded assets in their title to fit the changing action as users play the game. Or, they could create new assets on the fly from text instructions and optional audio inputs.
Making a Joyful Noise One of the model's capabilities we're especially proud of is what we call the avocado chair, said Valle, referring to a novel visual created by a generative AI model for imaging.
For instance, Fugatto can make a trumpet bark or a saxophone meow. Whatever users can describe, the model can create.
With fine-tuning and small amounts of singing data, researchers found it could handle tasks it was not pretrained on, like generating a high-quality singing voice from a text prompt.
Users Get Artistic Controls Several capabilities add to Fugatto's novelty.
During inference, the model uses a technique called ComposableART to combine instructions that were only seen separately during training. For example, a combination of prompts could ask for text spoken with a sad feeling in a French accent.
The model's ability to interpolate between instructions gives users fine-grained control over text instructions, in this case the heaviness of the accent or the degree of sorrow.
I wanted to let users combine attributes in a subjective or artistic way, selecting how much emphasis they put on each one, said Rohan Badlani, an AI researcher who designed these aspects of the model.
In my tests, the results were often surprising and made me feel a little bit like an artist, even though I'm a computer scientist, said Badlani, who holds a master's degree in computer science with a focus on AI from Stanford.
The model also generates sounds that change over time, a feature he calls temporal interpolation. It can, for instance, create the sounds of a rainstorm moving through an area with crescendos of thunder that slowly fade into the distance. It also gives users fine-grained control over how the soundscape evolves.
Plus, unlike most models, which can only recreate the training data they've been exposed to, Fugatto allows users to create soundscapes it's never seen before, such as a thunderstorm easing into a dawn with the sound of birds singing.
A Look Under the Hood Fugatto is a foundational generative transformer model that builds on the team's prior work in areas such as speech modeling, audio vocoding and audio understanding.
The full version uses 2.5 billion parameters and was trained on a bank of NVIDIA DGX systems packing 32 NVIDIA H100 Tensor Core GPUs.
Fugatto was made by a diverse group of people from around the world, including India, Brazil, China, Jordan and South Korea. Their collaboration made Fugatto's multi-accent and multilingual capabilities stronger.
One of the hardest parts of the effort was generating a blended dataset that contains millions of audio samples used for training. The team employed a multifaceted strategy to generate data and instructions that considerably expanded the range of tasks the model could perform, while achieving more accurate performance and enabling new tasks without requiring additional data.
They also scrutinized existing datasets to reveal new relationships among the dat
Most recent headlines
05/01/2027
Worlds first 802.15.4ab-UWB chip verified by Calterah and Rohde & Schwarz to be ...
04/08/2026
Dalet, a leading technology and service provider for media-rich organizations, t...
04/07/2026
April 7 2026, 19:00 (PDT) Detective Conan: Fallen Angel of the Highway Opens in...
01/06/2026
January 6 2026, 05:30 (PST) Dolby Sets the New Standard for Premium Entertainment at CES 2026
Throughout the week, Dolby brings to life the latest innovatio...
02/05/2026
Dalet, a leading technology and service provider for media-rich organizations, t...
01/05/2026
January 5 2026, 18:30 (PST) NBCUniversal's Peacock to Be First Streamer to ...
28/04/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
28/04/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
28/04/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
28/04/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
28/04/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
28/04/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
28/04/2026
Introducing Nx 3-Strip v2 - A Physics-Based Technicolor Reconstruction for DaVin...
27/04/2026
CES Power, a provider of infrastructure for live events, has announced the acquisition of three Ireland-based businesses: GH Energy Rental Ltd, Event Power, and...
27/04/2026
FuboTV Inc. has announced it is developing its Multiview feature for the Fubo streaming service on select LG TVs, including 2024, 2025, and newer 4K and 8K mode...
27/04/2026
Shade, a file management platform for creative teams, has announced a $14 million funding round led by Khosla Ventures, Construct Capital, and Bling Capital, br...
27/04/2026
The Audio Engineering Society (AES) will present the Immersive Audio Academy 12th Edition - Immersive Audio in All Flavors - on April 30, 2026, at 12:00 p.m. ...
27/04/2026
DAZN has announced DAZN48, a creator program for the FIFA World Cup 2026 that will recruit 48 creators - one representing each of the 48 qualified nations - to ...
27/04/2026
FloSports has announced exclusive streaming rights to four CrossFit competitions: Legends Del Mar: CrossFit Semi-Finals, Magic City Games, NorCal Classic, and t...
27/04/2026
Telestream has announced that Pulse, its software-defined test and measurement p...
27/04/2026
Shade has announced it is a Cloud Computing and Storage winner in the 2026 NAB Show Product of the Year Awards. Winners were selected by a panel of industry exp...
27/04/2026
Leading the NBA's video-ads platform, this Penn State grad is at the forefro...
27/04/2026
DAZN has expanded its international broadcast rights for the T100 Triathlon World Tour to include Africa. All races from the T100 calendar will be available for...
27/04/2026
NAB Show has announced the recipients of its 2026 Project of the Year and Product of the Year Awards at a ceremony at the Las Vegas Convention Center.
Each wi...
27/04/2026
DIRECTV has launched on Meta Quest headsets, becoming the first MVPD to offer live TV through the platform. The timing coincides with the stretch run of the MLB...
27/04/2026
TBL Team Boxing League has announced a broadcast agreement with MSG Networks to air all remaining Season 4 fights live across MSG's television and digital p...
27/04/2026
IP integration, interoperability, growth of intercommunications were key concerns for vendors and visitors alike
Attendees at the recently concluded 2026 NAB S...
27/04/2026
Behind The Mic provides a roundup of recent news regarding on-air talent, includ...
27/04/2026
A pro-audio emphasis, spectrum changes, and on-field audio mark the new products and enhancements to existing offerings
Microphones remain the primary point of...
27/04/2026
The Sports Video Group team was all over the NAB Show floor out in Las Vegas las...
27/04/2026
N r Spotify grundades f r 20 r sedan dominerades musikmarknaden av illegal nedladdning. Sedan dess har streaming bidragit till att teruppr tta betalningsvilja...
27/04/2026
Time on Spotify should feel meaningful and intentional, not something that slips...
27/04/2026
New modular multi-effects plug-in revealed
The latest plug-in from Brainworx delivers a modular set of effects designed to offer a convenient alternative to...
27/04/2026
Kit includes supercardioid & shotgun capsules
High-end mic manufacturer Schoeps have recently introduced another member of their Desert Island Set family. O...
27/04/2026
LA2A-inspired 500-series module arrives
Sound Skulptor have announced the upcoming launch of a new 500-series module that aims to recreate one of the most p...
27/04/2026
SSL-inspired compressor unit upgraded
Stam Audio are well known for their painstaking recreations of vintage audio gear, with their extensive product range ...
27/04/2026
Available for current Nielsen ONE Ads customers, this new capability predicts sa...
27/04/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
27/04/2026
Nippon TV's In-House Proprietary AI Solution AiDi Wins Product of the Year A...
27/04/2026
Outpost Introduces Unlimited Collaboration Model for Review and Approval Workflo...
27/04/2026
Ikegami Announces VFE-P07D Monocular OLED Viewfinder with Tiltable 3.5-inch LCD ...
27/04/2026
Custom Consoles announces the completion of a large Module-R desk and MediaWall monitor display mount for an expanded master control room at Gravity Medias West...
27/04/2026
Other World Computing Launches OWC Express 4M2 Ultra - Thunderbolt 5 Four-Slot N...
27/04/2026
Back to All News
Netflix announces El sobrino, the new film by Dami n Szifron s...
27/04/2026
Red Seat Ventures Announces Exclusive Multiyear Partnership with Kill Tony The Company is the New Monetization and Distribution Home for the Globally Popula...
27/04/2026
RT 2FM is calling on aspiring DJs across Ireland to take their shot at the spot...
27/04/2026
RT continues to champion Ireland's creative life this May, supporting a broad range of festivals, exhibitions and performances across music, theatre, liter...
26/04/2026
Back to All News
Director Yoon Jong-bin Returns with The Generals' (WT), A...
26/04/2026
Back to All News
Nine Queens, Starring Alvaro Morte and Patrick Criado, Starts ...
25/04/2026
In the heart of Mexico City, music, culture, and fashion converged last night as Spotify and Vogue Latin America welcomed guests to an intimate gathering at Soh...