Discussion about this post

User's avatar
Mark Pierce's avatar

The output vision improves as personalization and the AI's cross-exchange 'memory' of the user grows. Even within a single exchange, you can share your vision before asking for lyrics and musical direction to cross-pollinate in SUNO. (Make sure to tell it it's for use in SUNO.)

Also, an extremely short request with the auto lyrics settings in SUNO produces lyrics that sound like a cross between ipsum lorem and a stroke. I hope an example link is acceptable. https://suno.com/s/7w63OZocwJEmxsga

BodrevBodrev's avatar

Yeah, I was trying to write a cyberpunk racing song, there was the word "neon" on every other line. There are two features I'd welcome, I don't know if they are present in the paid version.

1. More control in the music generation. I want to be able to specify scale and chord progression.

2. I want to be able to edit the lyrics and potentially the music on the fly like Claude does with text. Right now if I try to slightly edit a result I liked, I get a completely different song, that's potentially worse.

I also found a guy on youtube who samples the voices of actors and singers and is able to incorporate them with Suno. I haven't looked deeper into it, but from what I saw it wasn't very complicated, so I'm guessing the next copyright lawsuit is coming from singers and voice actors.

10 more comments...

No posts

Ready for more?