Suno or Udio are everywhere right now. Their users create whole songs with prompts. The fact that the two companies have probably trained on millions of musicians who did not give their consent for using their music does not really seem to bother them. So far no judge has ruled if they are infringing copyrights. But there are also artificial intelligences that take care of the users in the datasets, like for example Delphos. The platform allows musicians to train their own "Soundworld" with their own songs. Each Soundworld has a special style of an artist and other can use them to create music. I have talked with one of the founder of Delphos, Ilya Tolchenev, about their AI and approach.
Any feedback? Contact me on my homepage:
I produced all of "The Illiac Suite" myself (with a little help from A.I.):
Voices: ElevenLabs
Music of the episode:
Music generated by Delphos
Thanks for listening!
...and check out my agency:
DISCLAIMER: The content displayed in this podcast, including but not limited to the musical renditions and AI voice synthesis, is intended solely for entertainment.