Hacker News Reader

Hacker News

Comment by albertzeyer | Hacker News Reader

Full thread

albertzeyer

Since 2020, there are a number of new models, for example:

- Stable Audio: https://stability-ai.github.io/stable-audio-demo/ https://www.stableaudio.com/

- MusicGen: https://ai.honu.io/papers/musicgen/

- MusicLM: https://google-research.github.io/seanet/musiclm/examples/

View on HN

But none of these is a significant improvement over Jukebox. I think at this point everyone is waiting for Jukebox2.

SunoAI is very good in my opinion.

I tried a dozen of different prompts in suno ai to generate some music - it completely ignored them. It just generated some simple pop sounding tunes every time. I’m not impressed.

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

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.

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.

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?

I have seen people create quite a variety of music styles on SunoAI. Are you using v3?

I just tried Suno and the results to me are terrible.

It seems designed for making pop music no one will listen to.

I have spent many hours with MusicLM making wild experimental music no one will listen to.

MusicLM has no problem making really weird sound combinations.

I just gave SunoAI some of my MusicLM prompts I have saved and the results are garbage. The problem with the AI test kitchen model though is the results sound like they are in mono.

The ultimate for me will be when we can make rap/hiphop no one will listen to.

Stable-audio and MusicGen sounds better than Jukebox.

But the best so far is Suno.ai ( https://app.suno.ai ) especially with their V3 model they have very impressive results, the fidelity is not studio quality but they're getting very close.

It's very likely based on their TTS model they have released before (Bark), but trained on more data and with higher resolution.

https://github.com/suno-ai/bark

Absolutely incredible: https://app.suno.ai/song/62ebaa5c-1651-430a-a034-ae2c75e61c2...

Reply on news.ycombinator.com