Stability AI has unveiled the latest generation of its music creation platform with the ability to produce a three-minute long ‘song’ track.
Stable Audio 2.0 is the new edition of the software which allows users to turn a text prompt into an extended piece of audio. With a maximum three-minute form, the standard length of a regular song, Stable Audio will produce an intro, main track, and an ending to the music.
It is an impressive feat, but how useful will the content be, and how much interest will there be in this instant form of artificial intelligence (AI) generated music which goes against the grain of creativity and artist expression?
Introducing Stable Audio 2.0 – a new model capable of producing high-quality, full tracks with coherent musical structure up to three minutes long at 44.1 kHz stereo from a single prompt.
Explore the model and start creating for free at: https://t.co/E9ZIGagmPf
Read the… pic.twitter.com/rFGb0KpdeX
— Stability AI (@StabilityAI) April 3, 2024
How does Stable Audio 2.0 work?
This review from End Gadget is a critical one which casts doubt on the prospects of the release from Stability AI.
With up to three minutes to fill, Stable Audio 2.0 provides a great tool for experimentation and fun. Depending on the quality and end product, it could work as an accompaniment to social media content but there is a limit on what can be created.
Stable Audio 2.0 works by text prompt, but there is an option to upload an audio clip which must be copyright-free.
The program will assess the upload before churning out something similar in response to the prompt. Without even being able to lean on existing music, expectations should be adjusted on what Audio 2.0 can provide.
It is essentially AI-generated music and there is no getting away from that. The instrumental aspects of the music are encouraging but the vocals are a reminder of the limitations of the software.
Stability AI’s offering is a fast product, able to construct a ‘song’ within 60 seconds with the content extended in length from 90 seconds to a possible three-minute duration thanks to the 2.0 update.
There will be uses for this audio but it doesn’t appear to present a serious breakthrough for original AI-generated music content. Not yet anyway.
Go give it a try, for free, at stableaudio.com
Image credit, Stability AI
The post “Stability AI music platform heralds three minute ‘song’ creation” by Graeme Hanna was published on 04/04/2024 by readwrite.com