
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...
21/08/2026
A massive deployment of specialty cameras, graphics, and AR will showcase the na...
21/08/2026
The West Coast Conference unveiled its new 30-second public service announcement, the latest expression of the Conference's We Rise in the West brand iden...
21/08/2026
New look will serve as the foundation for ESPN's upcoming NFL season and Sup...
21/08/2026
ESPN will air the ninth annual MLB Little League Classic presented by New York Life on Sunday, August 23, at 7 p.m. ET from Historic Bowman Field in Williamspor...
21/08/2026
In an emotional acceptance speech in Canton, Grossman celebrated the pioneering ...
21/08/2026
Hardware-style timing shifts for software instruments
Following on from the release of Omniclock, Rapid Flow have launched a new sequencer plug-in that can ...
21/08/2026
Highly anticipated synthesizer ships in October 2026
Iceland-based Love Synthesizers have announced that their highly anticipated synthesizer is now availab...
21/08/2026
Masterpiece PBS The Forsytes has expanded its cast as its begins production in ...
21/08/2026
The BBC has unveiled first-look pictures from The Witch Farm, a new ghost story and mystery set in the Welsh countryside, coming soon to BBC iPlayer and BBC One...
21/08/2026
The BBC and BritBox have revealed the first look of Edward Bluemel as Hercule Poirot in the forthcoming six-part series Hercule from Mammoth Screen and Agatha C...
21/08/2026
Our priority was making the best, most powerful, most meaningful story possible,...
21/08/2026
eds3_5_jq(document).ready(function($) { $(#eds_sliderM519).chameleonSlider_2_1({ content_source:......
21/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
21/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
21/08/2026
Avid will unveil how it is transforming production to help media organizations unite content, agentic workflows, and business insights at IBC2026 (RAI Amsterda...
21/08/2026
New routing, modular processing, orchestration and monitoring capabilities bridge dedicated hardware and software-based processing as part of the Dynamic Media ...
21/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
21/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
21/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
21/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
21/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
21/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
21/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
21/08/2026
When hundreds of thousands of people gather to hear a single voice, there is no room for compromise. Every word must be delivered clearly, every wireless transm...
21/08/2026
Telestream, a global leader in media workflow technologies, today announced a strategic partnership with ScorePlay, the AI-powered media infrastructure that spo...
21/08/2026
NUGEN Audio announces the launch of its new Post Plan and Producer Plan, two flexible subscription offerings designed to give audio professionals short term acc...
21/08/2026
Join the Screen Currency 2026 Ask Me Anything (AMA) Online 20 August 2026
(L-R): Adrian Coates, Grainne Brunsdon, Deirdre Brennan, Rachael Perkins
Got questio...
21/08/2026
Tell us a little bit about your job I'm a Marketing Manager and work across a mix of clients and projects. No two days are ever quite the same, which defini...
21/08/2026
Beat The Lotto dives into the plot behind the 1980s National Lottery scandal
24 August 2026 at 9:35pm on RT One and RT Player
Beat The Lotto is the story o...
21/08/2026
The countdown to the most wonderful night of the year has officially begun!
Host Patrick Kielty is gearing up for another unforgettable Late Late Toy Show nig...
21/08/2026
Meet puppet duo Bellie and Whizz, who are about to explore all the big feelings ...
20/08/2026
From host-broadcaster and rightsholder support in June and July to MLS, NWSL, US...
20/08/2026
In-venue and creative video staffers at the professional and collegiate level ha...
20/08/2026
At IBC this year, Veritone (14.A56) is bringing two connected themes to the booth: architectural independence in enterprise AI, and the automation of the media ...
20/08/2026
Telestream and ScorePlay have announced a partnership combining Telestream's...
20/08/2026
The Grand Slam of Curling and Rock League have announced a three-year agreement with ESPN, bringing more than 300 hours of live curling coverage to U.S. audienc...
20/08/2026
Nielsen has announced a series of enhancements to its Big Data + Panel currency measurement methodology, taking effect August 31. The updates were developed in ...
20/08/2026
Net Insight has been selected by service provider Big Blue Marble (formerly ORS Group) to provide its Nimbra platform as the core media transport solution for a...
20/08/2026
The 2026 US Open will bring a series of free fan activations across New York City ahead of and during the tournament, which runs August 23-September 13.
We...
20/08/2026
Bridge Technologies will announce a transport stream (TS) playout feature for its VB330 and VB220 compressed monitoring probes at IBC2026 (Booth 1.A71).
The fe...
20/08/2026
ENCO will demonstrate solutions across captioning, translation, AI production tools, automation, and virtual production at IBC2026 (Stand 7.A34, Amsterdam RAI, ...
20/08/2026
MultiDyne Video and Fiber Optic Systems will demonstrate camera robotics and mot...
20/08/2026
Chyron will demonstrate news workflow solutions at IBC2026 (Stand 7.A23), marking the company's 60th anniversary. Highlights include updates to PRIME HTML, ...
20/08/2026
Spectrum SportsNet LA, the exclusive television home of the Los Angeles Dodgers, is now available to Spectrum customers in former Cox markets following the clos...
20/08/2026
swXtch.io will unveil expanded Global SRT Distribution and native multicast tran...
20/08/2026
Riedel Communications has announced that Transformation Church in the United States has deployed a communications system built around the Artist intercom ecosys...
20/08/2026
The bestselling author and longtime Apple observer explores how product launches...