The Stability AI music tool now allows you to produce songs up to 3 minutes long

Unsplash/Pawel Czerwinski

Concerns have been growing about the challenges generative AI poses to human talent in the creative industries, and an update from Stability AI on Wednesday will only increase those concerns.

The London-based startup has just released Stable Audio 2.0, the latest version of its music generation platform.

It claims the update offers “a new standard in AI-generated audio,” with the ability to create high-quality complete tracks with a coherent musical structure, and up to three minutes in length (twice the original version) at 44.1kHz stereo. .

When it launched in September last year, the tool offered text-to-audio capabilities, but version 2.o incorporates a new audio-to-audio feature that lets you upload audio samples (must be copyright free) and convert them into various sounds using commands natural language.

Stability AI shared a YouTube video showing how audio input can be used to create new music.

“Stable Audio 2.0 differentiates itself from other advanced models because it can produce songs up to three minutes long, complete with structured compositions that include intros, builds and outros, as well as stereo sound effects. ” AI Stability said in a blog post on his site.

This new model is available to use now — for free — on the Stable Audio websiteSo if you think there’s a punch inside you that’s bursting at the seams to come out, why not give it a try?

Be aware of lawsuits from various creatives Angry that their work was used to train AI models without any offer of payment, Stability AI pointed out in its blog post that Stable Audio 2.0 was trained exclusively on a licensed dataset from the AudioSparx music library consisting of over 800,000 audio files, “respecting the choice-issue demand and ensure fair compensation for creators.”

The launch comes just days after Billie Eilish, Nicki Minaj and other artists expressed concerns over AI’s impact on the music industry. The pair are among more than 200 artists who share an open letter calls for protection “against the predatory use of AI to steal artists’ voices and likenesses.”

Editor’s Recommendations

Leave a Comment