zubzubi

I find it depends how you generate it. Asking Suno to make covers of uploaded recordings tends to give much, much better results than asking it to cook a song from scratch. There are still quite a few tells that it's AI-made but it's not bad at all, at least in my experience so far.

Yes I'm already doing this manually with Reason. I'll compose something that's quite bare bones, export the audio and run it through Suno, asking it to cover and improvise with a specific style, then when I have something I like, I split that into stems, import some or all of these to Reason and then reconstruct and enhance the sound using instruments in Reason, mostly by replaying the parts I like on keyboard and tweaking it in the piano roll. Often I get additional inspiration just by doing that. Eventually I delete all the tracks that came from Suno stems when I've finished this process.

That way I get new musical ideas from Suno but without any trace of Suno in the final output. Suno's output, even with the v5 model, is never quite what I want anyway so this way makes most sense to me. Also it means there's no Suno audio watermarking in the final product.

Can it do differently-styled covers of songs or improvisations upon melodies like Suno can?

As a musician, that's what I find most compelling about Suno. It's become a tool to collaborate with, to help test out musical ideas and inspire new creativity. I listen to its output and then take the parts I like to weave into my own creations.

The AI music tools that generate whole songs out of prompts are a curious gimmick, but are sorely lacking in the above.