dcoscina
Senior Member
Geez… it’s creepy but cool to hear a real sung part for text I’ve entered. Once this becomes a plug in for notation apps I could see really benefiting from this technology.
UDIO AI- short serial piece for baritone and orch
- Thread starter dcoscina
- Start date
tc9000
Absolute Member
Geez… it’s creepy but cool to hear a real sung part for text I’ve entered. Once this becomes a plug in for notation apps I could see really benefiting from this technology.
jbuhler
Senior Member
What did you use for the prompt on this? I'm just curious how much and what kind of direction you gave.Geez… it’s creepy but cool to hear a real sung part for text I’ve entered. Once this becomes a plug in for notation apps I could see really benefiting from this technology.
OP
OP
dcoscina
Senior Member
yes indeed. I wish I could claim credit for the music but it's largely AI with some text prompts from me. Some interesting ideas however which I will likely employ in a more customized manner.Great piece!
Did you write the lyrics?
OP
OP
dcoscina
Senior Member
I cannot wait until this type of technology allows us render our music with the same realism. Analyzing notation and/or MIDI date with CCs. I do think the first step is programs like Dorico/MuseScore/Sibelius because there can be a lot more performance related instructions notated on the score. If I could get a result like this on my current cantata I would be in 7th Heaven!
soundofmaw
Casual Observer
Is it just me, or does that really sound like Pavarotti's voice?
Cletus McBone
(Formerly: R.G.)
I'm taken aback by some of these voices. Does anyone have any notion of how in the fudge that baritone voice is being created?
__________
__________
tc9000
Absolute Member
shhhhh! the lawyers will hear!
Noeticus
Motion Picture Producer
Was this really the prompt for the above?Geez… it’s creepy but cool to hear a real sung part for text I’ve entered. Once this becomes a plug in for notation apps I could see really benefiting from this technology.
"Instrumental, Modern classical, Classical music, Western classical music, Minimalism, Avant-garde, Repetitive, Serialism"
Noeticus
Motion Picture Producer
jbuhler
Senior Member
I found this article somewhat helpful:
Audio Diffusion: Generative Music’s Secret Sauce
Exploring the principles behind diffusion technology and how it is being used to create groundbreaking AI tools for artists and producers.
towardsdatascience.com
tc9000
Absolute Member
The prompt was the first line: modern classical, serialism, atonal, contemporary classical, haunting endingWas this really the prompt for the above?
"Instrumental, Modern classical, Classical music, Western classical music, Minimalism, Avant-garde, Repetitive, Serialism"
I think the second line is some sort of categorisation? Not sure
tc9000
Absolute Member
OP
OP
dcoscina
Senior Member
The one thing to mention here is that I could lift this audio and transcribe much of it into notation if I really wanted to. I’ve actually written serial pieces before so I’m familiar with this style. And some of the orchestration techniques here give me some great ideas to apply to an original work.
StefanoM
Senior Sound Designer & Composer
Pavarotti, Bocelli, and many others, musicians, composers, sound designers, singers, everyone has potentially been used without their knowledge to gather information ( and talent ) for training.
There are copyright infringements everywhere. Guys. Maybe you are not realizing, that HERE there is a BIG problem of copyright !
The amount of data that has been analyzed without anyone's authorization is simply frightening.
Just another example...of copyright problem on this AI technology...
THIS IS of course a TRAINING on ANDREA BOCELLI !
And this is NOT ACCEPTABLE!"
There is nothing exciting or beautiful in all this. Considering that this is NOT making music.
Last edited:
