
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
06/10/2025
France T l visions, France's leading broadcaster, has received the 2025 EBU ...
04/09/2025
Monumental Sports & Entertainment (MSE), in collaboration with Dalet, has been a...
07/08/2025
July 8 2025, 22:30 (PDT) Tata Motors & Dolby Bring Dolby Atmos to Harrier.ev, R...
18/07/2025
Blanche Barton, Peter Gilmore, Scott Cummings, Sundance Institute Director of Programming Kim Yutani, and Peggy Nadramia throwing horns. (Stephen Lovekin/Shutte...
18/07/2025
By Jessica Herndon
One of the most exciting things about the Sundance Film Fest...
18/07/2025
BOSTON Sports network NESN today relaunched the NESN 360 app with a redesigned user experience and upgrades....
18/07/2025
Berklee Singers Wow the Competition on Netflixs Building the Band Netflixs new music competition show features two Berklee artists looking to make their pop b...
18/07/2025
As the House of Representatives voted early Friday morning to eliminate federal funding for public broadcasting, advocates warned that the elimination of $1 bil...
18/07/2025
DENVER Imagine Communications has announced that it is deepening its commitment to the North American sports and live events market with investments in its prod...
18/07/2025
LOS GATOS, Calif. Netflix once again reported strong financial growth, with revenue increasing 16% year-over-year to $11.079 billion in Q2 2025 as net income s...
18/07/2025
Live from the 153rd Open Championship: SMT Enhances Video Board Experience; Enab...
18/07/2025
ShotTracker's Davyeon Ross on Revolutionizing Basketball On the Court and ...
18/07/2025
Home Pitch: How the Danish League Brought Its Live Match Production In-House Matchday Production produced 800+ matches across Denmark in its first year By Geor...
18/07/2025
Live From the 153rd Open Championship: EMG Debuts Spidercam for Golf, Expands Su...
18/07/2025
Usyk vs Dubois II: Bringing the fight to life with state of the art cameras and ...
18/07/2025
Usyk vs Dubois II: DAZN's head of boxing Chris Glanville talks helicopters, ...
18/07/2025
Live From the 153rd Open Championship: NBC Expands Unilateral Effort; Shared Stu...
18/07/2025
Warner Bros. Discovery's Anne Graham on Training New Professionals to Ensure...
18/07/2025
Live From the 153rd Open Championship: How R&A Spidercam Became a Reality for Go...
18/07/2025
ESPN Bulks Up Onsite Studios, Cameras, Player Mics for WNBA All-Star Weekend Besides the game, four studio shows will be produced onsite By Jason Dachman, Edit...
18/07/2025
Friday 18 July 2025
Credit: Marc Sethi
The Sky Arts Awards will return on 16 September, once again taking place at the iconic Roundhouse in London. Produced b...
18/07/2025
This month, players can dive into special crossover events featuring SpongeBob SquarePants in Snake.io+ and Crossy Road Castle, available exclusively on Apple A...
18/07/2025
Up for the Match brings the fun, the passion-and a bit of Riverdance- tomorrow n...
17/07/2025
Blanche Barton, Peter Gilmore, Scott Cummings, Sundance Institute Director of Programming Kim Yutani, and Peggy Nadramia throwing horns. (Stephen Lovekin/Shutte...
17/07/2025
Spotify's goal with audiobooks is to help grow the publishing industry and create the best possible experience for booklovers, which is why we're launch...
17/07/2025
An advanced large solid rocket motor hot fire test conducted at L3Harris' Camden, Arkansas, site....
17/07/2025
L3Harris payloads and components have been on board every U.S. GPS satellite-more than 70 missions since the 1970s. Our technology is at the core of GPS availab...
17/07/2025
L3Harris' pack of launched effects is comprised of multi-role vehicles that ...
17/07/2025
NEW YORK - July 17, 2025 - Gracenote, the content data business unit of Nielsen, has announced the appointment of Ryan Moore to the new role of Chief Business O...
17/07/2025
READING, Pa. Network technology startup Miri Technologies has added David Cohen as vice president, business development. He'll be tasked with expanding the ...
17/07/2025
Berklee Wins CASE Award for Standout Digital Campaign The Alumni Affairs team's Variations Signature Series earned recognition for offering an authentic p...
17/07/2025
Early Thursday morning, the U.S. Senate voted to cut federal funding for PBS and NPR in a bill that also included cuts for foreign aid. In a 51-48 vote, the act...
17/07/2025
GREAT Britain and Northern Ireland Pavilions across IBC2025 (12 15 September, RAI Amsterdam) feature a remarkable 34 companies, each providing unique, innovativ...
17/07/2025
WHITE PLAINS, N.Y. The Society of Motion Picture and Television Engineers today introduced its Content Provenance and Authenticity (CPA) in Media Study Group (S...
17/07/2025
NEW YORK Despite widespread concerns about a soft advertising market, NBCUniversal said it closed its 2025-26 upfront negotiation cycle with a record ad sales v...
17/07/2025
NEW YORK Television advertising remains an effective means to market and influence younger baby boomer and Generation X consumers approaching retirement age, ac...
17/07/2025
ALLENTOWN, Pa. & JERSEY CITY, N.J. Service Electric Cable TV and OpenVault have announced that the operator is deploying the OpenVault Proactive Network Manage...
17/07/2025
WASHINGTON Following up on his first major policy speech just two ago, Federal Communications Commission Chair Brendan Carr is promising to buck the usual summ...
17/07/2025
Luxembourg, 14 July 2025 - SES received the final regulatory approvals for the SES-Intelsat transaction, including the US Federal Communications Commission.
O...
17/07/2025
Berklee Alumni Nominated for 2025 Emmy Awards Twenty-seven Berklee alumni received nominations across categories in sound mixing, sound editing, and compositi...
17/07/2025
Back to All News
What We Watched the First Half of 2025
Entertainment
17 July 2025
Global
Link copied to clipboard
Today, we're sharing our latest Eng...
17/07/2025
Cast your vote in 2 categories for Ivory 3 American Concert DIvory 3 American Concert D is in the 2025 MIDI Innovation Awards and we are honored to be nominated...
17/07/2025
SVG Sit-Down: OpenDrives' Sean Lee, Michael Wilsker, and Jason Matousek on E...
17/07/2025
Oracle's Geoff Tognetti on Staying Ahead of the AI Curve Through Further Ado...
17/07/2025
NBA's Summer League Is a Hot Bed of AI, Immersive Innovation Testing Audio mixing, intelligent camera framing are among AI-driven efforts By Ken Kerschbaum...
17/07/2025
SVG's TranSPORT Conference Returns to NYC on Oct. 21; Register Today! By SVG Staff
Thursday, July 17, 2025 - 8:29 am
Print This Story | Subscribe
St...
17/07/2025
Gravity Media chosen as group name for merged OB business By George Bevir
Wednesday, July 16, 2025 - 11:30
Print This Story
Gravity Media executive chairm...
17/07/2025
SES Closes Deal to Acquire Intelsat, Creating New Giant in Satellite Connectivit...
17/07/2025
How MLB Pulled Off That Unforgettable Hank Aaron Tribute at the All-Star Game Vintage content, state-of-the-art projection/processing combine in marvelous mile...
17/07/2025
Wuppertal July 17, 2025
Riedel Communications Powers Handa Opera on Sydney Har...