Earlier this year, we ran a story on the updates of Udio and Suno – generative AI tools trained on colossal archives of existing music, and, therefore, primed and ready to immediately concoct fully-fledged and arranged tracks in response to user prompts.
Our initial take was one of skepticism, with its text-generated results resulting in – as our writer Matt Mullen opined – “Largely bland, uninspiring tracks that you could imagine soundtracking a joyless insurance commercial.”
But it was the other addition, that of taking the fragments of audio ideas from music-makers, and building out full tracks from the most rudimental of starting points, that excited us the most.
While certainly useful for those at a creative crossroads, the implications of using an audio extender of this type were worrisome.
Was that finished, AI-augmented track really YOURS? Or is it a collaboration between yourself and an AI (and an AI that’s been trained on archives of music by other artists, we might add).
