Connect with us

Hi, what are you looking for?

Tech News

AI-generated songs are getting longer, not necessarily better

A brain with wires over a field of music notes
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 that 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 Limitless Pendant comes in a bunch of colors and doesn’t really look like an AI gadget. | Image: Limitless The Limitless Pendant doesn’t...

Tech News

The Dbrand Ghost Case for the iPhone 15 Pro. | Image: Dbrand Dbrand is scrapping plans to fix its anti-yellowing Ghost Case, but not...

Editor's Pick

Michael F. Cannon Any day now, the Biden administration could issue a regulation that, if it mirrors what the administration proposed in July, would take...

Editor's Pick

Krit Chanwong and Marc Joffe On February 28, 2024, Mississippi’s House of Representatives voted overwhelmingly to approve the expansion of the Medicaid program to...