Udio's New Feature is a Gamechanger for AI Music
Summary
TLDRIn this video, the host explores the new AI-generated music feature released by Udo, which allows users to upload their own music and extend it with AI. The host tests the feature with various prompts and music styles, demonstrating its ability to generate unique tracks and lyrics. They also experiment with AI voice models, creating a John Mayer-like vocal track, and discuss the potential for further experimentation and the limitations of the current technology, such as the inability to separate individual tracks.
Takeaways
- 🚀 AI-generated music has made significant advancements with the release of Udo's new upload feature.
- 🔗 There's a tutorial available for understanding how Udo works, linked in the description.
- 💰 The new 'Extend Your Own Audio' feature is available for paying users, not just those on the Pro Plan.
- 🎹 The feature allows users to upload their own music and extend it with AI-generated content.
- 🎼 The script includes a demonstration of extending a solo piano piece performed by a world-class musician.
- 🎶 Udo captures the characteristics of the original recording and matches them in the AI-generated output.
- 🔄 There are limitations to the feature, which are discussed in the script.
- 🔁 The script explores experimenting with AI by stacking different AI-generated tracks to create unique sounds.
- 🎤 Udo can generate music with user-provided vocals, but there are challenges in getting it to sound like a specific artist.
- 🎧 The script includes an example of using AI to generate music in the style of John Mayer using a vocal sample.
- 🛠️ The potential of AI in music creation is highlighted, including the ability to inspire new ideas and techniques.
Q & A
What is the main topic discussed in the video script?
-The main topic discussed in the video script is the new upload feature of an AI music generation tool called 'udio', and how it has advanced in creating music based on user-uploaded audio.
What is the significance of the 'extend your own audio' feature in uadio?
-The 'extend your own audio' feature in uadio allows users to upload their own music and have the AI generate new music based on the uploaded audio, which is a significant leap in personalizing AI-generated music.
Is the new feature only available to users on the Pro Plan of uadio?
-No, the new feature is not exclusive to the Pro Plan. The script mentions that the user only has the standard plan and still has access to the new feature.
What is the basic concept of the new uadio feature?
-The basic concept of the new uadio feature is to allow users to upload a short snippet of their own music and then provide prompts to uadio to generate an extension or continuation of that music in a style of their choosing.
What is the role of the piano piece performed by a world-class musician in the script?
-The piano piece serves as an example to demonstrate the capabilities of the new uadio feature, showing how a short snippet of music can be uploaded and extended by the AI.
What is the name of the collaborative track mentioned in the script?
-The name of the collaborative track mentioned in the script is 'Rain on Glass'.
What is the significance of the four-chord loop in the script?
-The four-chord loop is used to show how uadio can take a simple musical idea and generate an entirely new piece of music in different styles based on the user's prompts.
What is the result of combining multiple AI-generated tracks from uadio?
-Combining multiple AI-generated tracks can result in a more complex and layered piece of music, as demonstrated in the script where the combination of tracks created a sound similar to a theme song for an HBO crime drama.
What is the process of using AI to generate music with vocals?
-The process involves using a tool like Aon to generate a vocal track from a sample, and then using uadio to generate instrumental tracks based on the vocal sample and given prompts.
What challenges did the user encounter when trying to generate music with the voice of John Mayer?
-The user encountered challenges with generating lyrics that matched the vocal melody and the style of John Mayer. The initial results sounded unnatural, and the user had to use additional tools like chat GPT to refine the lyrics.
What is the potential workaround for generating music with specific vocals like John Mayer's?
-A potential workaround suggested in the script is to generate an a cappella version of the vocals first and then generate an instrumental track based on that, merging the two to create a complete song.
What is the user's opinion on the future of AI-generated music tools like uadio?
-The user believes that AI tools like uadio shine in their ability to inspire and assist in the creative process, providing new ideas and directions that the user might not have thought of otherwise.
Outlines
🎼 Exploring AI-Generated Music with Udo's New Feature
The video script introduces a significant advancement in AI-generated music with Udo's new upload feature. The narrator spent time experimenting with the feature, pushing it to its limits. It's clarified that the feature is available to paying users, not just those on the Pro Plan. The feature allows users to upload their own music and create extensions before or after their song. A demonstration is given using a solo piano piece, showcasing how Udo captures the characteristics of the original recording. The narrator also discusses limitations and the potential for further exploration with the new model.
🎹 Experimenting with AI Music Generation and Kit Bashing
The script continues with the narrator's exploration of Udo's AI music generation capabilities. Using a four-chord loop from a collaborative track, the narrator demonstrates how Udo can extend and transform the music into different genres, such as indie rock electronic and downtempo. The process of stacking different AI-generated tracks to create a complex composition is discussed, highlighting the creative potential of combining multiple AI outputs. The narrator also touches on the topic of generating music with AI using a user's own voice, referencing a previous video and the use of a tool called Aon to create a John Mayer-like vocal performance.
🎤 AI Music Generation with Custom Vocals and Guitar
In the final paragraph, the narrator delves into the use of AI for creating music with custom vocals and guitar parts. They experiment with using a John Mayer vocal sample and Udo to generate a blues rock track, encountering some challenges with the initial results. The narrator then uses Chat GPT to refine the lyrics and re-inputs them into Udo for a better outcome. The script concludes with a humorous anecdote about creating an 'AI John Mayer' performance at a fictional venue, reflecting on the creative possibilities AI tools offer for generating unique musical ideas and the current limitations regarding vocal generation.
Mindmap
Keywords
💡AI Generated Music
💡udio
💡Music Extension
💡Paying User
💡Solo Piano Piece
💡Kit Bashing
💡Indie Rock
💡DAW (Digital Audio Workstation)
💡Aon
💡Lyrics Generation
Highlights
AI-generated music has made significant advancements with the release of Udo's new upload feature.
The new feature allows users to upload their own music, enhancing the extension feature of Udo.
The feature is available to both standard and Pro Plan users, contrary to previous reports.
Udo's new model captures the characteristics of the original recording for extension.
A basic demonstration showcases a solo piano piece transformed into a classical extension.
Experimentation with a four-chord loop from the song 'Rain on Glass' resulted in unique AI-generated tracks.
The AI took the chords and arpeggiated them, creating a new genre-appropriate track.
Stacking different AI-generated tracks can create complex and atmospheric compositions.
AI can generate lyrics and entire songs from simple chord loops.
Experimentation with vocal samples and AI models like Aon can mimic artists' styles.
A vocal hook sample was transformed into a John Mayer-like rendition using AI.
Udo's advanced features allow for customization of generation quality and lyric strength.
AI-generated music can struggle with generating lyrics that match the original vocal melody.
Chat GPT can be used to refine AI-generated lyrics for better coherence.
Combining AI-generated vocals and instruments can produce unexpected and creative results.
The potential workaround for generating a complete song with vocals and instruments involves using separate AI models for each.
AI tools like Udo are expected to evolve, with stem separation being a highly anticipated feature.
The comparison between Udo and other AI music generators like Sunno is noted, with anticipation for their upcoming features.
Transcripts
so AI generated music has taken a
massive leap forward with the release of
udo's new upload feature today we're
going to dive into this new feature and
I spent some time this morning like
really digging into it I ended up
pushing things in some pretty
interesting directions using some kit
bashing trying to break it basically uh
yeah you're definitely going to want to
check this out okay let's dive in so
first off if you actually need a walkr
of how UD works there is a tutorial that
I did earlier that is linked down below
secondly this new extend your own audio
is only available if you are a paying
user I think it was previously reported
that you had to be on the Pro Plan in
order to use this that is not true I'm
actually only on the standard plan and I
have access to it so this new feature is
basically a spanked up version of their
extension feature which allowed you to
you know create extensions after your
song or before your song at an intro or
at an outro the difference this time is
that you can upload your own music so
kicking off with a very kind of basic
version of this uh here is a solo piano
piece performed by a worldclass musician
down in Studio A I'll tell you more
about that in a second uh let's go ahead
and
[Music]
listen and that is how you tickle the
ivories now that's only 3 seconds you'll
actually hear the entire piece in a
video next week I'm going to hold off on
telling you who the surprise guest is
but if you've been following the channel
there's a pretty good chance you've
figured it out anyhow uploading that
short snippet and then giving udio The
Prompt classical piano contemporary
classical just keeping it very simple uh
and we're going to use the ad section
after we end up with
[Applause]
[Music]
this and that is pretty impressive now
admittedly I have a bit of a bias
considering that I have heard the
original record Rec ing uh and you will
too next week don't forget to hit that
subscribe button but I think what's most
interesting and fascinating to me is the
fact that this new udio model actually
takes the characteristics of the
recording and matches to that I haven't
had a chance yet to EQ and sweeten that
recording so what you heard was pretty
much just you know microphone recording
and udio really did capture those
characteristics now there are some
limitations on that front and we'll talk
about that in just a little bit so
here's where things get really
interesting so I ended up taking a four
chord Loop that I recorded for a song
called rain on glass this was a
collaborative track that I did with the
UK producer named palid it's kind of one
of those like sleepy ambient Loi tracks
it's up on Spotify Apple music and all
those other streaming services if you
want to listen to it hey look uh 11,000
listens meaning that we made about 2
cents off of that streaming royalties
are a whole other rant video we're not
going to get into that now so very
briefly here are the chords
[Music]
those four chords more or less Loop and
we just put some ornamentation around it
now let's see what udio does with it so
running it through as an instrumental
track and giving it an extension uh we
ended up with neon Drifter the prompts
here were indie rock electronic
downtempo and left field uh let's take a
listen to what we got
[Music]
so not bad definitely within genre and
what's interesting is that it ended up
taking my chords and kind of
arpeggiating them now udio does generate
two tracks per you know generation the
second one I wasn't necessarily
incredibly Blown Away with at first
[Music]
so in this case it did end up using the
original chords but then adding in a lot
of like weird atmospheric stuff and that
got me thinking well what would happen
if we started stacking these things so I
brought them into a DA digital audio
workstation uh I use Ableton you can
pretty much use any audio editor that
you want to accomplish this so on this
track I just have you know those
original guitars that we supplied udio
with the second track was our
atmospheric e one and the third track
was the generation that had the heavier
bass and drums but when we turn turn all
three of them on it suddenly sounds like
it's the theme song to a new HBO crime
drama
[Music]
now while that can use some editing I
think one of the coolest things about
all of this is there's no such thing as
a bad or off generation in fact if
anything it just kind of makes you want
to experiment more for example you know
on the channel I definitely tend to lean
more towards instrumental stuff although
we do have some pretty crazy vocal stuff
coming up in just a minute so while
experimenting I decided to let udio take
that four chord loop again uh I just
changed out the prompt to Indie pop and
let udio write lyrics and we ended up
with this me what's your heart's desire
make it clear don't let it hide I just
got to see what's your favorite
Skyline what you wish a star tell me am
I on your mind do we
align is this
fine
oh I just got to
[Music]
see so yeah that's pretty much a song
and we can kind of just keep generating
iterating cutting and looping and you
know very easily come up with a 3 to 5
minute long original song and that's
without any other stem separation or
fancy tricks although obviously if you
have fancy tricks you could probably go
even crazier with this which does lead
us into crazy kit bashing territory so
one of the questions that's probably
most asked every time that I do a story
on an AI music generator is can I upload
my own voice and have it create you know
a song and the answer to that is yes
sort of we're going to go into a really
weird Direction here caveat I am not
singing you do not want to hear me sing
instead we're going to revisit an old
video that I did and one that nobody
watched cuz it was on AI girlfriends in
the back end of that video I ended up
taking a look at a tool called ampon
This is a model that will generate from
a trained voice off of a voice input so
with Aon I ended up taking a vocal hook
sample and turning it into John Mayer
quick side note despite being a white
dude in his 40s that plays guitar I'm
actually not the biggest John Mayor fan
nothing against him I think he's an
incredible guitar player I I've tried to
learn neon numerous times it's very hard
but I do like his stuff with the trio
and actually have seen him a couple of
times with the Grateful Dead maybe I do
like John Mayor damn you mayor so anyhow
taking this vocal sample is it really
love is it really love or am I just
falling for the things they could call
it l but in you I trust let's forget
about the world cuz you're where I want
to be and running it through Aon with
the John Mayor model we end up with this
is it is or am
iing for the same things they could call
it l but in you I trust let's forget
about the world cuz you're where I want
to be yeah Anana is kind of crazy I'm
glad you guys are catching it now cuz
again nobody saw it in the AI girlfriend
video so loading that John Mayor sample
into udio and giving it you know prompts
like blues rock and uh let's do like
drums bass guitar and then not giving it
any custom lyrics Just To See what'll
happen uh I do want to just point out
something here if you actually prompt
for John Mayer as well you'll actually
end up with a little no no prompt uh it
won't actually give you John Mayer
instead it will replace it out with
things like male vocalist Americana
singer songwriter North American music
all the country I guess uh and mellow I
should add under the advanced features
you have things like generation quality
uh you should probably just crank that
up to ultra uh the lyrics strength as
well the higher that you kick it the
possibly more accurate the anunciation
will be but may not sound as rhythmic
and natural um we're just going to leave
that here and then for our prompt
strength we're just going to leave that
I'm going to take that up to 66 why not
uh let's run this and see what we get
the initial results were not that great
in fact if anything it just kind of ends
up sounding like John mayor's having a
stroke let's take a listen to
stratospheric strut here saying I'm for
the same
things so interestingly it still sounds
like John Mayer and it definitely has
like this kind of rhythmic flow to it it
kind of sounds a little bit like a demo
version of a song that he might be
writing that he hasn't figured out the
lyrics for I do have a solve for this
we're going to talk about that in one
second but I just before we did I I have
to play you Continuum drift because uh
this one just makes me laugh
John if you need do do do backups on
your next album give me a call so really
I think the problem came down to the
fact that udio just really wasn't able
to generate lyrics at that front end it
was just it did have vocal Melody so
what I decided to do was take the lyrics
that uh we initially had bring them over
to chat GPT and listen I Know lyrics and
chat GPT look this is a YouTube video
I'm not going to pour my heart out like
writing lyrics for this so bringing that
back over to udio we ended up with
something that actually came out pretty
good the fact we could take it
slow we could take it
slow every moment with
you feels like a
dream but life so fall love
to so interestingly it does fumble in
the transition between our initial set
of lyrics and our sample lyrics There's
kind of like this jumble of words there
in the center but I think if you wanted
to use this you could probably just edit
that section out now I will say that the
downside to all of this is that I was
not able to get a ban behind John Mayer
no matter how much I prompt or remixed
or extended backwards or forwards but
when I initially created that John Mayor
voice in the AI girlfriend video my AI
girlfriend is a huge fan of John Mayor
by the way I decided to have a little
fun with it so I decided recorded track
underneath it let's check that out real
quick for the sa they could call it l
but you trust let's forget about the
world cuz you're want to be thank you
for indulging me there AI John Mayer and
I are playing the Dairy Queen this
weekend it's boob so bringing that track
into udio the results were both
absolutely stunning and mid at the same
time it was really weird uh let's take a
listen to in my arm
in particular note how much better a
guitar player udio is than I
[Music]
am we could take it slow we could take
it slow every moment with you feels like
a dream when you're in my arms in my
arms Nothing Else Matters it's just you
and me is there
any so yeah it's actually pretty cool I
mean the biggest thing to notice is that
Jon's voice obviously is very different
from the sample that we provided but man
that udio guitar player definitely gave
me some pretty cool ideas in another
generation and I'm just going to play a
quick second of this uh udio just
decided to go full John frante with my
guitar John frante the guitar player
from the Red Hot Chili Peppers
straightup guitar genius uh he is very
much a guitar players
[Music]
[Applause]
guitarist we could take slow this is
where I think that udio and AI Tools in
general really shine I probably never
would thought of going full like
Hendrick's feedback for that opening but
you know now that I've heard it I could
either you know maybe use it if I wanted
to cheat it or I could go out and learn
it and record it now as far as the John
voice I don't really have a trick for
that yet but I do think there would be a
workaround by generating up an Acappella
and then generating up a track after
that and then merging them together I
actually don't have time to try that out
today let me know in the comments if you
would like to see me give that a go and
before anybody starts yelling at me in
the comments yes I do do know that sunno
has a very similar feature that is
getting ready to release I re I mean
what can I say I reached out toso I
asked if I could try it out and you know
I never heard back from them regardless
I do think that sunno will be dropping
that soon and then after this I think
the only real major thing that we're
going to be looking for is the ability
to be able to separate out the
individual tracks so I'm curious to see
who gets to that one first until then I
thank you for watching my name is Tim
Просмотреть больше связанных видео
![](https://i.ytimg.com/vi/Wm5qoH7dqlY/hq720.jpg)
Tutorial Suno AI Completo: Crea Musica con l'Intelligenza Artificiale in Pochi Passi
![](https://i.ytimg.com/vi/jz6EKwahWp8/hq720.jpg)
Creo MUSICA con l'AI CANTICCHIANDO A CASO - Demo Stable Audio 2.0 (GRATIS)
![](https://i.ytimg.com/vi/mCpgbeFwGuY/hq720.jpg)
Udio: un'AI ASSURDA per creare musica (anche cantata) [Demo]
![](https://i.ytimg.com/vi/pJwYlNSuMEI/hq720.jpg)
AI Rendering ADDED TO SKETCHUP! But is it worth using?
![](https://i.ytimg.com/vi/ZxYAtL0D50A/hq720.jpg)
You’ve NEVER Heard AI Music Like This :(
![](https://i.ytimg.com/vi/Y8nzHOWHC6g/hq720.jpg)
This Ai Tool Makes Full Music Videos With Only One Prompt
5.0 / 5 (0 votes)