
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...
03/09/2026
NEP Group has announced leadership changes at Creative Technology Group. Founder and CEO Graham Andrews will step away from day-to-day leadership at the end of ...
03/09/2026
The NFL and TikTok have announced a multi-year partnership renewal expanding the league's presence on the platform. NFL posts on TikTok increased more than ...
03/09/2026
Grass Valley has appointed Ronny Van Geel as Vice President, Cameras. Van Geel began his career in 1999 at Philips DVS and moved into product management in 2005...
03/09/2026
Telestream has announced Vantage Super Resolution, an AI-powered upscaling capability for the Vantage media workflow platform, developed in collaboration with N...
03/09/2026
Solid State Logic (SSL) will debut the TCA Tour at IBC2026 (Hall 8, Stand 8.B45), a portable production system built from System T components in a desktop frame...
03/09/2026
DPA Microphones has announced the 6388 CORE Headset Microphone, making its debut at IBC2026 (Hall 8, Stand D60). The supercardioid headset features a physicall...
03/09/2026
Qvest will present a multi-vendor Dynamic Media Facility (DMF) showcase at IBC2026 (Booth 10.C24), demonstrating how the EBU's DMF architecture can be imple...
03/09/2026
Imagine Communications will showcase the Magellan PanelFlex control surface and other control portfolio updates at IBC2026 (Stand 1.B73, RAI Amsterdam, Septembe...
03/09/2026
Bridge Technologies will announce at IBC2026 (Booth 1.A71) that its VB440 production probe is now available as a software-based solution, deployable on commerci...
03/09/2026
Audio-Technica has unveiled the BP350ST MS (mid-side) microphone in two versions: the camera-mount BP350ST-UL and the boundary or gooseneck-mountable BP350ST-UB...
03/09/2026
Telos Alliance will introduce updates to the J nger Audio flexAI audio processin...
03/09/2026
DUNKMAN, the professional dunk league founded by Shaquille O'Neal in partner...
03/09/2026
Orlando's WRDQ TV 27, WFTV Channel 9 previously named over-the-air broadcast...
03/09/2026
EverPass Media has announced a multi-year commercial distribution agreement with Netflix, expanding on an existing partnership that has delivered NFL Christmas ...
03/09/2026
Yahoo Sports and Apple TV have announced a partnership to deliver alternate broadcasts of select Friday Night Baseball and MLS games on the Yahoo Sports website...
03/09/2026
With another academic year underway, college athletic departments across the cou...
03/09/2026
Facility becomes permanent home of NFL Live on Sept. 9; centerpiece studio for c...
03/09/2026
Create musical synth bass sounds from scratch
Anthony Marinelli Music have recently announced the launch of Bass DNA, a new online course that teaches music...
03/09/2026
Most powerful Tonex hardware to date
IK Multimedia's latest release introduces their most advanced Tonex hardware unit to date, combining their AI Machi...
03/09/2026
Upmix & downmix software upgraded
Penteo Audio Plugins have announced that the latest version of their powerful upmix and downmix software is now available....
03/09/2026
With the start of the new apprenticeship year, young talent has once again begun their professional careers at SGL Carbon's sites in Germany. Recently, the ...
03/09/2026
With the industry increasingly embracing hybrid, software-defined production models, Calrec will preview a series of Argo and ImPulseV software enhancements at ...
03/09/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
03/09/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
03/09/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
03/09/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
03/09/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
03/09/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
03/09/2026
Recognizing the ever-increasing demands for media throughput in challenging environments like post-production, two leaders in network technology have worked tog...
03/09/2026
EVS, a leader in live video technology and production infrastructure solutions, and Matrox Video, a leader in software-defined media technology and IP-based vid...
03/09/2026
AJA Debuts OG-FiDO-4 openGear Four-Channel SDI/Fiber Conversion Cards
Brie Clayton September 3, 2026
0 Comments
New product family expands 12G-SDI and...
03/09/2026
Nice Touch launches V2 of its AI edit assistant for professional editors
Brie Clayton September 3, 2026
0 Comments
Built by two editors with twelve ye...
03/09/2026
Accedo, a global provider of video streaming software and services, and MediaKind, a world-leading video technology company and the number one independent provi...
03/09/2026
International research from Big Blue Marble puts a consumer churn number against a technical failure, and sets out what streaming providers must fix before 2030...
03/09/2026
High-performance points of presence power video streaming delivery to large audiences across Latin America with guaranteed quality of experience
Broadpeak , a ...
03/09/2026
Dalet, a leading technology and service provider for media-rich organizations, will unveil the next evolution of Dalia at IBC2026 (7.A43), its media-aware agent...
03/09/2026
CGI (TSX: GIB.A) (NYSE: GIB), one of the world's largest independent IT and business consulting services firms, will showcase CGI OpenMedia Evolve and CGI d...
03/09/2026
LiveU is participating in the IBC Accelerator Incubator 2026: Smart Stories The New Knowledge Architecture for Content Production, an industry-wide initiative...
03/09/2026
Broadcast Solutions, a leading systems integrator and provider of innovative solutions for the broadcast and media industry, has taken another major step in its...
03/09/2026
Quortex today announced that it will showcase how it is accelerating innovation and the transition to IP at IBC 2026. The company will debut its newest intellig...
03/09/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
03/09/2026
The EZDRM approach to Revenue Security on streaming video can be visualized as a multi-dimensional set of solutions. A growing dimension of that approach is the...
03/09/2026
From field capture to management, control and production, Kiloview will demonstrate one connected Hybrid AV-over-IP workflow including a complete 4RU producti...
03/09/2026
Mediagenix, a global leader in smart content solutions to profitably connect the right content to the right audience, today announced Mediagenix Curation, a new...
03/09/2026
LucidLink, the Emmy-winning cloud-native file streaming platform for instant, secure access to large files, today announced the next step in its vision to make ...
03/09/2026
Fraudulent communications purportedly from Screen Australia 3 September 2026
Screen Australia is aware of scam attempts involving fake emails and promotional m...
03/09/2026
AJA Introduces FS8, Next-Gen 12G-SDI/SMPTE ST 2110 Media Processor
Brie Clayton September 2, 2026
0 Comments
AJA Video Systems unveiled FS8, a video a...