
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...
15/05/2026
Join Calrec at MPTS 2026 | May 13-14 | Stand A40 | Olympia, London We're looking forward to meeting up with customers and partners at this year's Media ...
15/05/2026
86% of media planners would move more linear TV budget to CTV if they had show-level targeting and reporting - and 65% would also shift dollars from programmati...
15/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
15/05/2026
Clear-Com will showcase new communications solutions and major platform updates at InfoComm 2026 (Booth N7005), June 17-19, in the North and Central Halls of t...
15/05/2026
Following an outstanding inaugural year in 2025, Rise AV is proud to announce the return of its flagship leadership initiative, Elevate. The programme continues...
15/05/2026
Berklee Announces Lineup for Inaugural AI Music Summit The three-day event puts musicians at the center of the future of music creation, ethics, and the indus...
15/05/2026
Lightware returns to InfoComm 2026 with a focused showcase of scalable USB-C connectivity, next-generation AV-over-IP solutions, and technologies that help over...
15/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
15/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
15/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
15/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
15/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
15/05/2026
Delivering a live, arena-scale production of a massively popular band is no small feat. Between expansive in-arena LED walls and a global live stream fed to onl...
15/05/2026
Connection is the heartbeat of any strong community, and with live streaming becoming more accessible in the modern era, it's much easier for faith-based or...
15/05/2026
Powered by GX 3 media servers, optimised IP-VFC workflows and on-site engineering expertise, the production delivers high-performance visuals for one of the wor...
15/05/2026
Against that backdrop, IAB UK has added retail media to its Gold Standard. Jan Pitt, Commercial Director at ABC, spoke with Liv McCullagh, Retail Media Lead at ...
15/05/2026
Further to RT 's statement released yesterday and in the interest of full transparency, with the full permission of Derek Mooney, we are now publishing the ...
14/05/2026
Sweetwater and Airstream have announced a custom-built Dolby Atmos mobile recording studio inside an Airstream trailer, set to tour music festivals, schools, tr...
14/05/2026
The American Association of Professional Baseball (AAPB) has announced a new par...
14/05/2026
ESPN has announced plans to transform Santa Monica Beach into a broadcast hub du...
14/05/2026
Amagi has announced a significant update to Amagi CLOUDPORT, its cloud-based broadcast playout platform. The update includes 250-plus features shipped in FY25-2...
14/05/2026
Clear-Com will exhibit at InfoComm 2026 (Booth N7005, June 17-19, Las Vegas Convention Center), introducing a new product that builds on Arcadia Central Station...
14/05/2026
Ikegami will exhibit at BroadcastAsia 2026 (Stand 5D3-1, Singapore Expo, May 20-22), introducing two new viewfinders alongside its existing camera, control, and...
14/05/2026
Grass Valley has announced that dB Broadcast has delivered new IP-based outside ...
14/05/2026
NAGRAVISION, a Kudelski Group company, has announced a partnership with the World Professional Billiards and Snooker Association (WPBSA) to launch Play Snooker,...
14/05/2026
Belden Inc. has announced a definitive agreement to acquire RUCKUS Networks from Vistance Networks for approximately $1.85 billion. The transaction has been app...
14/05/2026
NVIDIA has released the Content Localization Blueprint, a modular reference arch...
14/05/2026
Disney has announced that Disney will be the exclusive U.S. streaming home of the Banana Bowl, the Banana Ball league season championship, streaming live this ...
14/05/2026
Arkona technologies and technology partner manifold will demonstrate their production solutions on the Magna Systems and Engineering stand (Booth 5D1-1) at Broa...
14/05/2026
Haivision will host a webinar on Thursday, May 21 at 10 a.m. ET / 4 p.m. CET cov...
14/05/2026
The CW Network and ESPN have announced a sublicense broadcast agreement for The CW to televise ACC football and men's and women's college basketball gam...
14/05/2026
The agreement marks Scripps Sports' first NBA local rights deal...
14/05/2026
A new report from education-technology company Wiingy testing post-ChatGPT predictions against three years of real-world data has identified broadcasting as one...
14/05/2026
Global Citizen and FIFA have announced that Madonna, Shakira, and BTS will headl...
14/05/2026
LOS ANGELES, CA, May 14, 2026 - The nonprofit Sundance Institute announced today the cohort selected for the 2026 Episodic Lab program, taking place at Dunaway ...
14/05/2026
At Spotify, we're focused on making every listening experience feel intentio...
14/05/2026
Spotify recently welcomed songwriters, artists, executives, and music students t...
14/05/2026
New articulations, ostinatos, Motion Scoring Articulation Sets & more
Sonuscore's flagship cinematic string library has just been treated to a significa...
14/05/2026
World-class studio opens on T rkiye's Aegean coast
P r Recording & Residence have announced their official opening, introducing a new world-class reside...
14/05/2026
Now supports channel layouts up to 9.1.6
Nugen Audio have just released an update for their AI-powered dialogue intelligibility and compliance tool. Set to ...
14/05/2026
New recordings & one-key chord tool
UVI have just announced the release of Orchestral Suite 2, a ground-up redesign of their all-in-one symphonic orchestra ...
14/05/2026
Two new arrivals & expanded factory content
Rob Papen's all-encompassing plug-in and virtual instrument collection has just been treated to another upda...
14/05/2026
Embed QR codes into DAW sessions
FSK Audio's latest plug-in doesn't process audio, but serves as an organisational tool that allows QR codes to be e...
14/05/2026
SBS Board appoints Jane Palfreyman Managing Director
13 May, 2026
Media releases
The Special Broadcasting Service (SBS) Board of Directors is pleased to an...
14/05/2026
Transforming bold ideas into market-ready productions: Digital Originals returns
14 May, 2026
Media releases
SBS, NITV and Screen Australia have announced ...
14/05/2026
Australia Uncovered Returns to SBS with Bold New Season Featuring John Safran on...