Many of the first wave of Generative AI breakthroughs involved creating insanely realistic images and videos from simple text prompts. Innovations with the potential to disrupt Hollywood while democratizing filmmaking and turning anyone into an artist. In just a short period of time the quality and realism of these AI creations have advanced to the point where people are now getting regularly fooled, unable to tell the difference between what’s real and what’s not. And now AI is coming for the music industry as well. Thanks to Udio, a ChatGPT like service for music.
Ars Technica explains:
“Between 2002 and 2005, I ran a music website where visitors could submit song titles that I would write and record a silly song around. In the liner notes for my first CD release in 2003, I wrote about a day when computers would potentially put me out of business, churning out music automatically at a pace I could not match. While I don’t actively post music on that site anymore, that day is almost here.
On Wednesday, a group of ex-DeepMind employees launched Udio, a new AI music-synthesis service that can create novel high-fidelity musical audio from written prompts, including user-provided lyrics. It’s similar to Suno, which we covered on Monday. With some key human input, Udio can create facsimiles of human-produced music in genres like country, barbershop quartet, German pop, classical, hard rock, hip hop, show tunes, and more.”
Adds Rolling Stones:
“Just last year, many experts believed an AI model capable of generating complete, high-fidelity songs from text prompts wouldn’t arrive anytime soon, but now, an arms race is on between competing music-making models that do just that. Suno‘s v3 model, released to the public just weeks ago, was a remarkable breakthrough, particularly in realistic, human-sounding vocals — and today, a formidable new competitor arrives via the just-launched startup Udio. The two companies’ output seems closely comparable, though some early users have suggested that on average, Udio‘s output may sound crisper than Suno‘s, with less of the sonic fuzziness that can betray tracks’ machine-created origins. “
What’s really cool about Udio though is the ability to combine the AI generated music with AI generated imagery to fit the piece:
I was inspired recently by the movie Yesterday to want to become a song writer. Even though I don’t have any musical talent I do have experience as a writer and a poet that could come in handy when trying to come up with lyrics. Perhaps Udio would be perfect for someone like me. Taking raw lyrics or just an idea and instantly producing music that people could enjoy without the need for having to sing or play an instrument myself. A week ago my dream of becoming a song writer would have been a virtual impossibility. But now that’s a very realistic possibility.
Move over Yesterday. The future has arrived.
Is Udio the Greatest Idea Ever?
Leave a comment