
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 ...
07/10/2026
Dalet, a leading technology and service provider for media-rich organizations, today announced the latest Long-Term Supported (LTS) release of Dalet Flex. Build...
06/09/2026
June 9 2026, 23:00 (PDT) Dolby and MagentaTV Bring Fans Closer to the FIFA Worl...
18/08/2026
SportStream 2026, a free three-day virtual event, will take place September 15-17. One registration provides access to all three days of live programming and on...
18/08/2026
BeckTV will introduce BeckFlow to the European market at IBC2026, demonstrated on the Providius stand (10.F53).
BeckFlow is a web-based schematic documentation...
18/08/2026
Boland Communications will introduce a SMPTE ST 2110 input option for its 4K monitors at IBC2026, along with a new 55-inch super-narrow bezel display for video ...
18/08/2026
Dolby Laboratories and the Seattle Seahawks have announced a partnership integrating Dolby OptiView into the Seahawks' live streaming coverage, making the S...
18/08/2026
For BMG Executive Producer of Sports Production, Graham Taylor, producing live s...
18/08/2026
TMRW Sports has appointed Rufus Hack as President of Golf, a newly created role in which he will lead the company's golf businesses including TGL presented ...
18/08/2026
SMT will provide race technology for FOX Sports' coverage of the Freedom 250 Grand Prix of Washington, D.C. on August 23, when the NTT INDYCAR SERIES races ...
18/08/2026
The live, YouTube-native roundtables combine fan voices, credentialed reporters,...
18/08/2026
Behind The Mic provides a roundup of recent news regarding on-air talent, includ...
18/08/2026
The industry legend sounds off on replacing the Heat's iconic Medusa score...
18/08/2026
William F. Rasmussen, the sports fan-turned broadcaster and entrepreneur whose out-of-the-box idea of a 24-hour cable sports network, ESPN, changed forever the ...
18/08/2026
DAZN Group has completed its acquisition of ViewLift, a provider of streaming and digital solutions for sports content owners. The acquisition was first announc...
18/08/2026
The American Association of Professional Baseball (AAPB) has added SI TV, Sports Illustrated's 24/7 streaming channel, as a broadcast partner for the remain...
18/08/2026
The Esports Foundation has announced that the inaugural Esports Nations Cup (ENC), originally scheduled for November 2026 in Riyadh, will be postponed to Novemb...
18/08/2026
Diversified has announced a new Global Managed Services Practice, consolidating the company's managed services capabilities into one organization. Rob Mello...
18/08/2026
Appear has completed a proof of concept with Thoroughbred Racing Productions (TRP), demonstrating multi-camera remote live production over bonded 5G cellular an...
18/08/2026
Riedel Communications has announced that Edith Cowan University (ECU) in Perth, ...
18/08/2026
Company launch with stereo-imaging tool
Panoramic is the debut release from Panorama Labs, a new company formed by mastering engineer Nicholas Di Lorenzo. C...
18/08/2026
Control software now available for older interfaces
Focusrite have just announced the launch of an update that extends Control 2 software support their Scar...
18/08/2026
The National Film and Video Foundation (NFVF), an agency of the Department of Sp...
18/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
18/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
18/08/2026
Lightware announces an integration with SpectralBot that helps system integrators and AV operators troubleshoot faster using augmented reality (AR), AI-assisted...
18/08/2026
Command Frame for After Effects
Scott Black August 18, 2026
0 Comments
Free download, demonstrations, hands-on tests, and creator resources
Want to t...
18/08/2026
At Stand 14.A57, the data company will demonstrate GreenDot and IBM Aspera together, giving media and entertainment businesses real-time visibility of what thei...
18/08/2026
New tool provides a robust audit of operational workflows, calculating the tangible value each delivers today, and informing business decisions for tomorrow.
W...
18/08/2026
Media Utilities is integrating its activities into DigiNet and will maintain a recognisable presence in the market under the name: Media Utilities, a DigiNet br...
18/08/2026
Proof of Concept validates reliable multi-camera live production from remote racecourses without fixed network infrastructure
Appear ASA (Appear, OSE:APR), a g...
18/08/2026
Stingr, a new venture from the founders of Hornets Tech, is bringing its second-screen interaction platform to IBC2026.
The second screen has never really wor...
18/08/2026
Long-established satellite equipment manufacturer and systems integrator Hiltron Communications will promote its new HACUX-IDU2 antenna control unit touchscreen...
18/08/2026
EMAM, PlayBox Neo and SNEWS Launch Combined Nuvex System
Brie Clayton August 17, 2026
0 Comments
Integrated platform melds media asset management, pla...
18/08/2026
The United Stand Scales Live Fan Show with Blackmagic Design Workflow
Brie Clayton August 17, 2026
0 Comments
ATEM Constellation 8K and HyperDeck Stud...
18/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
18/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
18/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
18/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
18/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
18/08/2026
Triveni Digital Now Offers a Joint Solution With MediaKind and a Lab System Bundle Supporting ISDB-Tb and TV 3.0 Broadcast Services
Triveni Digital, a trusted ...
18/08/2026
At IBC2026, BeckTV, a premier systems integrator for the broadcast industry, will introduce BeckFlow to the European market. BeckFlow is the first web-based sch...
18/08/2026
New flagship PTZ camera combines cinematic 4K imaging, professional broadcast connectivity and the complete Horizon intelligent video experience for productions...
18/08/2026
At IBC2026, VisualOn will demonstrate how video service providers can slash bandwidth costs, maximize ad revenue, and deploy premium interactive features withou...
18/08/2026
The relationships built during graduate school often continue to shape careers long after a degree is earned, creating a community of scientists who learn from ...
18/08/2026
Tuesday 18 August 2026
Sky Sports and The Fast and the Curious announce new partnership
Sky Sports and The Fast and the Curious have announced a new long-term...
18/08/2026
Wuppertal August 18, 2026
Riedel Brings Professional Live Production Into the Classrooms of ECURiedel Communications today announced that Edith Cowan Universi...
18/08/2026
In my previous article, The AI Shift Feels Familiar. Our Response Should Be Different., I argued that the greatest challenge organizations face is no longer the...
18/08/2026
Apple today announced changes to its business terms for apps in the European Uni...
18/08/2026
THE HEALY RAES: BLOOD, SWEAT & TEARS AIRS WEDNESDAY AUGUST 19 ON RT ONE AT 9:35PM
A new documentary The Healy-Raes: Blood, Sweat & Tears airs on RT One and ...