The wait is over and the rumors are true. Generative music startup Uncharted Labs today launched its own music generator called Udio. Transform simple text prompts into professional-quality tracks, and you’re ready to give the current king of AI music, Suno V3, a run for its money.
Before its official release, a few songs produced by Udio were leaked by anonymous sources, and the quality was impressive to say the least. With consistent lyrics, well-structured compositions, and rhythms that can rival human-composed tracks, some reviewers have already praised Udio as the best song generator to date, beating the Suno V3 at its own game.
The first teaser emerged last weekend when some accounts in the AI community shared a hip-hop song leak and another vintage-themed song featuring a very talented female voice.
The company remained silent at the time, but now Udio appears to have proven the rumors to be true, sharing a high-quality sample that matches the quality leak.
“We build AI tools to power the next generation of music creators,” Udio says on its official website. “We believe that AI has the potential to expand musical horizons and enable anyone to create extraordinary music.”
Introducing Udio, the app for music creation and sharing that lets you create amazing music in your favorite styles through intuitive and powerful text prompts.
1/11 pic.twitter.com/al5uYAsU5k
— udio (@udiomusic) April 10, 2024
Now open for public testing, the platform has already seen a huge influx of users eager to try out the new technology. However, this popularity caused server overload, resulting in wait times of over 30 minutes for both songs to be produced. For comparison, generating a song using the Suno V3 takes about 90 seconds. However, this issue may normalize in the coming days as traffic stabilizes.
decryption We attempted to generate some samples to compare with SunoV3, but the platform failed. When it collapses, it even displays a cute screen with a cool error-themed AI song.
Udio’s interface is user-friendly and intuitive. Users can create music by simply entering a description of what they want to create in the prompt box. For example, if you type “country song about Decrypt Media,” it will generate tracks that fit that description. Like other models, Udio also allows users to further customize their tracks by adding tags such as “soft” or “warm.”
Udio is supported by a16z, Black Eyed Peas musicians Will.i.am, Tay Keith, Steve Stoute’s UnitedMasters, Mike Krieger, Kevin Wall, and more. The company says it is committed to empowering artists and has several legal safeguards in its terms of service to ensure better model training and ethical use of its technology.
For example, users allow Udio to train future models with their creations, and artists cannot use Udio’s output for commercial purposes. These terms also restrict people from streaming other users’ content on social media and music platforms such as YouTube, Instagram, TikTok, SoundCloud or Spotify. However, the platform allows users to commercialize their creations.
Udio will remain free during its beta testing phase, and users will be able to create up to 1,200 songs per month when operational.
Editor: Andrew Hayward
