Musiio insists that if the human ear can hear it, AI can learn it. And they have the link to prove it.
The Singapore-based startup wants everyone to experience how AI curation works. It’s providing a window into this often misunderstood world with its new DIY AI. Drop your favorite YouTube video link here, and watch Musiio generate at least eight custom tags, including genre, BPM, key, and mood, in approximately 10 seconds.
Musiio has created an AI model that uses audio fingerprinting to surface, tag, sort, and playlist tracks swiftly, accurately, and on a massive scale. It has been trained on music from around the world and can recognize a great swath of the planet’s music, especially East Asian and Pacific styles and languages. For music that falls within its largest training sets, like Western pop, its accuracy easily hits 99%.
Read More: V Digital Services Brings the Heat in Phoenix
The DIY AI demo lets anyone play around with technology that promises to radically improve search, discovery, and curation, for everything from sync to ambient musical applications. “Smartphones and home studios have brought about the democratization of audio production, but one of the challenges for the music industry now is to figure out how to handle this volume,” explains Musiio co-founder and music tech veteran Hazel Savage, whose work has spanned the music business, from punk guitarist to record store clerk to an executive at Shazam. “It takes one person 83 days non-stop to listen to 40,000 new songs. Our AI can perform the task in under 4 hours. As music is created and released at a rate that is one million times greater than it was ten years ago, AI can solve problems that humans simply can’t.”
Alums of talent investors Entrepreneur First’s incubator and Midemlab finalists, Musiio first built a powerful tool for search, ideal for finding the right track in huge catalogs. Its fingerprinting technology–turning the audio file into mathematical visuals–allows someone to drop a file in and find 10-20 other files with similar sonic features, no tags or other metadata required. “We didn’t build it around assumptions of ‘this is what music is,’” explains Savage. “You don’t need data; you just need to train the model to match patterns.”
Read More: Revegy and FinListics Announce Partnership Alliance
As Musiio evolved, the team discovered that tags were in high demand. They taught their models to compare audio features, find similarities, and connect them with appropriate, completely customizable tags. The platform can also generate playlists based on these features.
Musiio aims to turn the firehose of music into manageable streams, teaching AI to listen for us and help us. “We’re focussed on the curation of music using AI, not on generation or other aspects of the creation and listening process,” reflects Savage. “It’s important because in our world, AI for music is not scary: it contains no sentience; it definitely isn’t a robot trying to steal your job, quite the opposite in fact. We aim to help artists be found and labels and streaming services to deliver a better, more personalized product.” It’s a service music fans are coming to expect and music-based businesses desperately need, one that Musiio makes possible.
Read More: LiveIntent Taps MediaMath Vet Jessica Muñoz as VP of Product Marketing
