Generating music in the waveform domain (2020)

Re:Generating music in the waveform domain (2020) by zaptrem on Tuesday March 26, 2024 @07:33PM (#39834067)

try this one my friend and I are training: https://sonauto.ai/

audio quality is still WIP and UI is ugly but prompting should allow more detail.

e.g., 70s Dolly Parton-style song rando made earlier today: https://sonauto.ai/songs/t4XGcHqsYwS6B73MjtV5

[ Parent | on HN ]

Re:Generating music in the waveform domain (2020) by throwway120385 on Tuesday March 26, 2024 @07:50PM (#39834159)

The lyrics on those songs are basically a pastiche of everything popular. But just based on sound it's pretty convincing. I bet you could train a generative AI to push out trance bangers as long as they don't have any lyrics.

[ Parent | on HN ]

Re:Generating music in the waveform domain (2020) by zaptrem on Tuesday March 26, 2024 @07:56PM (#39834199)

I mean the user wrote the lyrics (or maybe ChatGPT lol). People of course write more interesting ones (Just found a Ukrainian about Kyiv: https://sonauto.ai/songs/xRDqe57ZgT6QrFXiIzF0). There was another one about Frank Sinatra being attacked with a baseball bat but I can't find it rn.

[ Parent | on HN ]

Re:Generating music in the waveform domain (2020) by bradgpt on Wednesday March 27, 2024 @12:41PM (#39841460)

this is cool! i've played with stable audio a little but it doesn't do lyrics, how are you getting the vocals so good?

[ Parent | on HN ]