Menu
What's new
By:
Filters

Made with AI: Suno, Udio and others

driscollmusick

driscollmusick

Active Member
I've spent the past 24 hours being quite astonished at Udio, which I already consider vastly superior to any AI music generator I have heard to date.

To be clear: I share this for the purposes of awareness and conversation, not endorsement.

The lyrics I gave it were random text relating to a conversation I was having with a friend this morning. Since Udio only gives you 33 second clips, I had to extend it three times (adding an instrumental intro, 2nd set of text and final, largely instrumental outro)

BTW, as of this morning, Udio is claiming it is removes artist names (here "Richard Strauss") from the prompts, but as you can clearly hear (if you know his music), they must still be using it in the underlying mechanics

---
Good Morning Soo
The dogs need a walk
Can you hear them?
I hope you have a lovely day

Are you getting the groceries and the meal kits?
Yes, this day is for shopping.
How marvelous!
---

www.udio.com

Udio | Good Morning Soo - A Short Opera in the Style of Richard Strauss by Driscollmusick | AI Music Generator - Official Website

Listen to Good Morning Soo - A Short Opera in the Style of Richard Strauss by Driscollmusick on Udio. Discover, create, and share music with the world. Use the latest technology to create AI music in seconds.
www.udio.com www.udio.com
Click to read more...
 
Udio is currently indeed better than most AI music generators. However, it is not a threat to composers who can compose at an advanced level. I have a good idea of what will happen and I am already preparing for the near future. But for me, it is certain that any hobby composer who composes classical/new-age/film-music with only chord progressions and a melody will be sidelined. The libraries that want to survive will have to use filters to reject AI music, or else they will be inundated with superficial music. Although, many libraries already survive by commercializing music without actually selling it.
 
Composery said:
it is certain that any hobby composer who composes classical/new-age/film-music with only chord progressions and a melody will be sidelined.
Click to expand...
It seems I'm out of the game, then. Luckily, a "hobby composer" is just that: he doesn't have to make money from composing, unlike advanced professionals who don't care about melodies but can come up with masterpieces made of clusters and expertly crafted sound designs. I'm sure these professionals will never be replaced by an algorithm!
 
Sad to see how fast this is progressing. I hope they get sued for using non public domain training data in the creation of their product. I think there's absolutely no way they could have made this in an ethical way.

Maybe try getting it to reproduce something recognizable by prompting things like "gangnam"?
 
Hello,

Sorry to add this track made with udio AI to the this discussion, but except that there is no real coherence in the composition, a new level has been reached and we all need to be a little concerned by what is happening and really think about the future of making music for medias...

www.udio.com

Udio | Mirthful Overtures by Meaks | AI Music Generator - Official Website

Listen to Mirthful Overtures by Meaks on Udio. Discover, create, and share music with the world. Use the latest technology to create AI music in seconds.
www.udio.com www.udio.com

This track was a test to hear what this AI could do, i never heard an AI reaching this level of composition, orchestration AND production...
 
Last edited by a moderator:
The singing in this example is striking and it gives me hope that the underlying technology is there for much better classical singing VIs than we currently have. Synth V has been doing something similar for a couple of years now but classical singing has eluded it, whether that’s because it’s inherently more difficult or they haven’t developed voices with the capability is hard to say. That’s the hopeful side.

The piece itself I found less impressive, sort of at the level of a party trick where we feed the algorithm with banal text and see what it makes of it. It’s very fun of course.
 
I've been checking this site out too. I asked it to create a string quartet in a serial mode with modern and sonata as some criteria. I cannot say this is horrible. Some neat effects (like harmonics for the chordal passages). The solo violin part is, frankly, stunning. It's clearly generated from real performances, not samples. I hope that notation apps like Dorico or MuseScore embrace this technology so that the playback of notated original works can sound as amazing.

Since this kind of generation is slow, I would expect using NotePerformer largely for the composing process, but to provide sonically much more realistic results, I could see adopting this. And to be perfectly honest, I might be pretty happy with the AI result as opposed to begging and pleading for commissions with paltry rehearsals and single performances... just being completely transparent here.

www.udio.com

Udio | Chromatic Reflections by BartokRulz29

Make your music
www.udio.com www.udio.com
 
This is both fascinating and extremely frightening at the same time! One the one hand its incredible to play with the shiny toys, but on the other I do get a bit of uncanny valley, though at other times this can sound shockingly good also - and not rarely either.... this certainly does put us somewhere different than we were a few weeks ago somehow. I can recall hearing computer speech for the first time... this feels like that degree of an advance.
 
Pavoreal said:
Hello,

Sorry to add this track made with udio AI to the this discussion, but except that there is no real coherence in the composition, a new level has been reached and we all need to be a little concerned by what is happening and really think about the future of making music for medias...

www.udio.com

Udio | Mirthful Overtures by Meaks | AI Music Generator - Official Website

Listen to Mirthful Overtures by Meaks on Udio. Discover, create, and share music with the world. Use the latest technology to create AI music in seconds.
www.udio.com www.udio.com
Click to expand...
Wow ! This is a Big progress for the AI, the last example that i've heard a year ago (from a site i dont remember) was very robotic and soulless.

This on the contrary is much better !
 
Paul@Sydney said:
People have always asked when a choir version of SynthV is coming. Well, don't need that anymore, I found this on the Udio site: https://www.udio.com/songs/aeB8xs41ZKwSBZyHuKJejP
Click to expand...
Given the quality of its vocal outputs (and excellent attention to sung text), it doesn't really seem too much of a stretch to imagine AI-generated singing at a very high level in the near future. Of course what I would want is for it to sing my music, not generate its own.
 
jbuhler said:
The singing in this example is striking and it gives me hope that the underlying technology is there for much better classical singing VIs than we currently have. Synth V has been doing something similar for a couple of years now but classical singing has eluded it, whether that’s because it’s inherently more difficult or they haven’t developed voices with the capability is hard to say. That’s the hopeful side.

The piece itself I found less impressive, sort of at the level of a party trick where we feed the algorithm with banal text and see what it makes of it. It’s very fun of course.
Click to expand...
It's also very clearly cribbing from Der Rosenkavalier (both the intro and outro).
 
Louie said:
These examples are indeed impressive. But, these are not your original melodies, or am I incorrect in that assumption?

Just asking for clarification, I'm not bashing.
Click to expand...
My only input was text: "soprano aria in the style of Richard Strauss" and the specific lyrics. In a typically odd AI manner, it outputted a duet (0:33 to 1:06)! I then asked for an instrumental intro (it added 0:00 to 0.33), an extension of the original with some additional words (1:06 to 1:39) and finally an instrumental outro (1:39 to the end). Notably the outro includes voices even though I asked it to be instrumental and provided no text.
 
You must log in or register to reply here.
Top Bottom