Hi all - This is a follow up from a recent HN thread on AI generated music [1]. I posted some songs I've been making using Jukebox and there seemed to be a little interest on the "how-to"... I typed something up quickly.<p>Here's my music if you all are interested. I've been looking to make vocals / "singer-songwriter" type stuff, rather than electronica.<p>Youtube Playlist: <a href="https://www.youtube.com/watch?v=_lcCJzfXl50&list=PLaa32nLgVv" rel="nofollow">https://www.youtube.com/watch?v=_lcCJzfXl50&list=PLaa32nLgVv</a>...<p>SoundCloud: <a href="https://soundcloud.com/songshtr/sets/machinecroon" rel="nofollow">https://soundcloud.com/songshtr/sets/machinecroon</a><p>Github: <a href="https://songshtr.github.io" rel="nofollow">https://songshtr.github.io</a><p>The main challenge for me so far has been post-processing. Jukebox produces very "scratchy" / lofi outputs... and I've been DIY'ing with Audacity. Thinking of getting a track professionally mastered to see just how far the boundary is...<p>[1] <a href="https://news.ycombinator.com/item?id=31968456" rel="nofollow">https://news.ycombinator.com/item?id=31968456</a>