There are many AI models where you can enter text and generate songs. So words should describe the music you want to listen to in the end. But how does an artificial intelligence learn what music sounds like? Metadata must be associated with the songs so that descriptions are assigned. But that's not as easy for music as it is for images, for example. I talked about the difficulties with Paul Zgordan from Mubert and Roman Gebhardt from Cyanite.

Any feedback? Contact me on my homepage:

Dennis Kastrup

Or on instagram: The Illiac Suite

I produced all of "The Illiac Suite" myself (with a little help from A.I.):
Voices: ElevenLabs
Underlaying Music: Mubert 
Image: Dall-E

Links of the episode:
Whitney Houston - Bohemian Rhapsody  Queen AI cover

Track: "13 Degrees", Shryne

Music provided by https://slip.stream

Free Download / Stream: https://get.slip.stream/s1lqwc

Track: "This Is The Sign You’ve Been Looking For", RINGO

Music provided by https://slip.stream

Free Download / Stream: https://get.slip.stream/P80cQp

Track: "Nice Dream", RINGO

Music provided by https://slip.stream

Free Download / Stream: https://get.slip.stream/pF9c1A

Track: "Dancefloor Therapy", Mom Bod

Music provided by https://slip.stream

Free Download / Stream: https://get.slip.stream/oNlEGs

Thanks for listening!

...and check out my agency:
Wicked Artists

DISCLAIMER: The content displayed in this podcast, including but not limited to the musical renditions and AI voice synthesis, is intended solely for entertainment.