Connect with us

Hi, what are you looking for?

Tech News

AI-generated songs are getting longer, not necessarily better

Illustration by Alex Castro / The Verge

Stable Audio 2.0, an audio generation model for Stability AI, now lets users upload their own audio samples which they can then transform using prompts and create AI-generated songs. But the songs will not win any Grammys just yet.

The first version of Stable Audio was released in September 2023 and only offered up to 90 seconds for some paying users, which meant they could only make short sound clips to experiment with. Stable Audio 2.0 offers a full three-minute sound clip—the length of most radio-friendly songs. All uploaded audio must be copyright-free.

Unlike OpenAI’s audio generation model Voice Engine, which is only available to a select group of users, Stability AI made Stable Audio free and publicly available through its…

Continue reading…

You May Also Like

Tech News

The entry-level Apple Watch SE is a gateway smartwatch if there ever was one. | Photo by Amelia Holowaty Krales / The Verge Editor’s...

Tech News

There’s plenty of tech on sale for Presidents Day, from iPads to OLED TVs and everything in between. | Photo by Dan Seifert /...

World News

This article first appeared in The Early 202 newsletter. Not a subscriber? Sign up here. Last year was the least productive year in Congress...

Business

Boeing and Alaska Airlines have separately denied any legal responsibility for the injuries allegedly caused to dozens of passengers after a door-plug blew out...