
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 ...
29/04/2026
It was a delicate job in a 150-year-old venue laden with traditions. Begun at th...
29/04/2026
In annual event, the league gives startup companies the opportunity to prove the...
29/04/2026
Panel discussions, networking, and a facility tour will take place in the renova...
29/04/2026
(L-R) Derek Drescher, Coss Marte, and Syretta Wright have each other's backs. (Micheal Hurcomb/Shutterstock for Sundance Film Festival)
By Veronika Lee Cla...
29/04/2026
Combines EQ and harmonic distortion
Techivation's latest release is a simple EQ designed to offer quick control over a source's overall tonal balanc...
29/04/2026
Two new MPE controllers announced
Expressive E caused quite a stir when they released the Osmose, making the sort of expression that was once reserved for p...
29/04/2026
New modules & enhanced machine-learning
The latest version of iZotope's flagship restoration suite is now available, and now offers over 50 tools design...
29/04/2026
Surgeon Dr Jasmina Kevric wins 2026 Les Murray Award
29 April, 2026
Media releases
Australia for UNHCR and SBS are proud to announce that Dr Jasmina Kevric...
29/04/2026
Some people stumble into their passion. Julissa Padilla walked straight into a film vault. For her, entertainment was never just about the movies themselves. It...
29/04/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
29/04/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
29/04/2026
Clear-Com has appointed Brian Grahn as Market Outreach Manager of the Americas and Ben Turnwell as Business Development Manager for EMEA live, expanding their ...
29/04/2026
nxtedition is bringing its range of consolidated production tools to MPTS 2026, with new developments spanning transcription, editing, graphics and AI-assisted ...
29/04/2026
Quortex Switch to boost the streaming experience for Telxius customers, reaching millions of viewers worldwide
Synamedia and Telxius, the leading global connec...
29/04/2026
freispace, the leading ERP-as-a-Service platform for media and entertainment production, and Projective, a leading provider of post-production collaboration tec...
29/04/2026
DHD reports strong interest in its broadcast audio product range, exhibited at the April 19th-22nd NAB Show in Las Vegas. The event attracted a claimed 58,000 a...
29/04/2026
Student Spotlight: Alan Catz The Argentine film and game composer talks about working on League of Legends, receiving Berklee's BMI Award, and the lifelon...
29/04/2026
Jay Jennings Builds the Worlds You Hear on Screen The supervising sound designer behind A Minecraft Movie, The Meg, Letters from Iwo Jima, and dozens of other...
29/04/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
29/04/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
29/04/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
29/04/2026
29 Apr 2026
VEON and Kyivstar Fulfill Commitment to Invest USD 1 Billion in Ukr...
29/04/2026
Rhod Gilbert, Harriet Kemsley, Kae Kurd, Sara Pascoe and Vicki Pattison to take part in brand new series on free streaming service U
London, 29th April 2026: F...
29/04/2026
Wednesday 29 April 2026
Katie Price: Nothing to Hide, a Sky Original documentar...
29/04/2026
Re-examining the case of Ellie Williams and the wider story of grooming in the town of BarrowWednesday 29 April 2026
Sky announces upcoming documentary series ...
29/04/2026
Wednesday 29 April 2026
Jennifer Garner to lead an all-star cast in new Sky Exc...
29/04/2026
Back to All News
SUPERNOVA: GENESIS Reached a Peak Audience of More Than 6.5 Mi...
29/04/2026
Students and staff from Hills Road Sixth Form College in Cambridge ran a 4.5km course around the roads of Cambridge as part of their annual programme of sustain...
29/04/2026
The Dawn Chorus airs Sunday 3 May from midnight to 7am on RT Radio 1 and RT ly...
29/04/2026
Jin-Quan Yu elected to the National Academy of Sciences Yu is recognized for his pioneering work in synthetic organic chemistry.
April 28, 2026
LA JOLLA, CA S...
28/04/2026
The audio team for the entertainment event must blend speech intelligibility with full-range music reproduction while considering the broadcast
Last week's...
28/04/2026
The Pac-12 Conference has released an updated primary mark and logo as the starting point of the new league's brand identity. The mark was soft-launched acr...
28/04/2026
The DP World Tour and Amazon Leo have signed an agreement making Amazon's lo...
28/04/2026
Pixellot and HELIOS have announced an integration that automatically converts full-game hockey video into individualized shift videos for each athlete, without ...
28/04/2026
Daktronics has partnered with the Asheville Tourists to manufacture and install a new LED video display. The installation was completed in late 2025 and is now ...
28/04/2026
Eutelsat has announced the renewal of its partnership with PCTV, a content aggregation and distribution company in Mexico and part of Megacable Holdings, for co...
28/04/2026
Daktronics has partnered with the Gary SouthShore RailCats to install a new LED video display at U.S. Steel Yard, replacing the previous Daktronics display inst...
28/04/2026
Telos Alliance and the College Radio Foundation have announced that WWSU-FM of W...
28/04/2026
Golf viewership is growing. The 2025 Ryder Cup drew five million viewers in the UK, a 45% increase over the 2023 event. The US Open was the most streamed golf e...
28/04/2026
The CW Network and WWE, part of TKO Group Holdings (NYSE: TKO), have announced t...
28/04/2026
The Alliance for IP Media Solutions (AIMS) has announced that the Internet Protocol Media Experience (IPMX) suite of standards and specifications has been named...
28/04/2026
The 2026 NAB Show is in the books and the show once again served up a cavalcade ...
28/04/2026
Gray Media and RAJ Sports have announced Rose City SportsNet (RCSN), a new netwo...
28/04/2026
Today, we announced our First Quarter 2026 earnings, starting the Year of Raising Ambition with strong momentum across the business and continued innovation acr...