Transcription
This is the best open-source AI music generator you can use right now. It's called Aceep. And in this video, I'm going to go over some demos. I'm going to show you how to use it, plus show you some useful tips and tricks to make your generations even better. And of course, I'm going to show you how to download and install this locally so you can use it for free and unlimited times offline. Let's jump right in.
So this is a new AI music generator by Ace Studio and Stepf fun and it's really simple to use. It's basically like Udio or Sunno or Refusion. You simply specify the genre or what you want the music to sound like and you can add in some optional lyrics and then press generate.
So first of all, here are some of their demos.
[Music] It's not just a dream. It's the start of a way. Building the future where music will play. A modal that listens, a modal that grows. A step is the rhythm the new world knows. No more limits, no more lines. A thousand songs in a million minds. We light the spark. We raise the sound. A new foundation breaking ground. A step we take the leap into a world. Worlds fast and free. We shake the skies that never die. Aces step the beat goes on. Found strong. Found strong. A brand new dawn.
[Music] Very nice. Note that a few weeks ago I featured another open- source music generator called Yu, but this new one AEP is just a lot better. And just like Sununo and Udo, note that throughout the lyrics you can also add in these metatags like verse, pre chorus, and chorus, which we'll go over in a second.
Here's an example where the genre is alternative rock. Let's hear what this sounds like.
[Music] Bright lights flashing in the city sky. Running fast and we don't know why. Electric nights got our hearts on fire. Chasing dreams we'll never tire. [Music] in our eyes. Breaking shining loud above the crowd. Living life like we're unbound. Wild in the night so free. Feel the beat endlessly. Hearts collide in the midnight air. We belong. We don't have a care.
Very nice. This does sound like a legit rock song. The vocals and the instrumentals sound really realistic and dynamic. This is really impressive for an open- source tool.
Here we have electronic rap.
[Music] Waves on the base post in the turnas features grinding on the beats in the digital hustler midnight in sneakers. It did mispronounce some of the words throughout the lyrics, but you can always regenerate or impaint this, which I'll show you later.
All right, here's a really crazy one. So, the prompt is dubstep obscure. Dubep, dubstep, dubstep, darkness, dubstep, dubstep, fear, more dubstep. Just make this song as dubstep as hell. And then for the lyrics, we have some dude shouting and then some other dark terrorizing lyrics. Let's hear what this sounds like.
[Music] [Music] opens the steel. He rises blood to feel. Flames roar, darkens the sky. Weak ones tremble, all must die. Oh, [Music] American do this like heavy metal voice and it was able able to do a pretty insane drop. Plus, if you specify echoing growl in this meta tag, it actually does generate some echoing growl. Pretty impressive.
Next, if we do some ethereal dark liquid, deep baseline female vocals. And then for the lyrics, we do something like this. Let's hear what that would give us.
[Music] [Music] My very interesting. And then here's another example with a female voice with these lyrics.
[Music] Oh. Oh. N yeah yeah yeah.
[Music] That was pretty cool. Now it didn't actually sing the exact number of nas and yas and o's. It's kind of all over the place, but a pretty interesting experiment nonetheless.
Now, this can also do instrumentals. So, here is some saxophone and jazz. Let's hear what this sounds like.
[Music] It does sound like saxophone and jazz.
Here we have a sonata with piano, violin, B flat major, and [Music] algro.
[Music] Here is some tango with guitar classic.
[Music] This sounds beautiful and super realistic.
Here is some psychedelic [Music] [Music] trans.
Now, in addition to English, you can also generate songs in all these different languages. So, here are just a few examples.
Here is some Chinese electronic house.
[Music] And then here is a French example.
[Music] Here's a German example.
[Music] [Music] [Music] Now, I have no idea if that is correct. So, if you understand German, let me know in the comments below if this song is actually sung correctly.
And then here we have a Japanese song. And of course, it's going to be anime with cute kawaii vocals.
[Music] I don't know. [Music] [Music] [Music] Damn, that does sound like J-pop. I especially love the guitars and the melody is actually not bad.
Then next here is some Korean.
[Music] All right. Well, enough demos. Let's go over how and where to use it.
If you want to use this online, at the top of the page, they do have a free hugging face demo. And if you open it up, it looks like this. Or if you click on their GitHub, it also contains instructions on how to download and run this locally, which I'll go over later in the video.
Once you install it, the interface also looks like this. Now, let's go over what each of these settings mean and how you can use it.
First, here we have the audio duration. Note that if you set it to the default value of minus one, this doesn't mean it would automatically fit the song duration to the lyrics that you enter below. So keep that in mind. It's not actually going to automatically fit the song. This just means a random duration between 30 seconds and 4 minutes. So instead of leaving this as minus1, I tend to set it to an appropriate length based on how long my lyrics are.
And then here we have an audio to audio feature, which I'll go over in a second. Here we have the tags. So this basically specifies the genre or what you want the song to sound like. And then down here we have some lyrics.
And if you scroll down a bit, here we have some basic settings. Infer steps basically means how many iterations you want the AI to go through before giving you the generation. In general, the more steps you have, the higher quality the song will be, but at a certain point, you're going to get diminishing returns. So it seems like the sweet spot here is the default value of 27. If you want to generate this faster, you could set this to like 20 or something with the risk of sacrificing some quality. I'm just going to leave it at the default of 27.
And then for guidance, we actually have three different values that you can set. So this first guidance scale determines how literally you want the AI to follow both your specified genre and your lyrics. So if you drag this to the right, then it's going to follow your prompt and lyrics more literally. If you drag this to the left, it's going to be more creative and not follow your prompt as much. Let me set this back to the default value. However, you can also override this value by setting a separate guidance for the text prompt which you entered here. So, if you want the AI to really follow the genre that you specified, then you can drag this to a higher value. Note that as long as one of these values are greater than one, which this one is, then this overall guidance scale will be ignored. So, let me reset this back to zero.
And then guidance scale lyric. You can also drag this to a higher value if you want the AI to really sing out your lyrics more literally and accurately because sometimes it does add in some filler words or mispronounce some words, in which case you might want to adjust this setting to a higher value. For me, I'm just going to reset this to zero for now.
And then over here, we also have some advanced settings. So, theuler is basically the algorithm that you want it to use to generate your music. You can select from these two here, plus some different types of CFG. So, feel free to play around with these settings. It might give you some subtle differences, but I just tend to leave everything at the default.
All right, so let's try generating a song. I'm going to select all of these lyrics and paste in some random lyrics which I generated with chat GBT. And note that for here I don't have a full song. I just have a verse and then a pre chorus and then a chorus. So I'm going to set the duration to 90 seconds which I think should be enough. This is just a rough estimation. And then for here let's just do a simple one for now such as pop rock. And that's pretty much it. Let's click generate.
All right. Here's what we get.
[Music] You wore your heart on a thrift store sleeve. Told me stories no one else would believe. Said the world was cruel, but I was kind. So I traced your pain like a dotted line. We were magic in the moment, wild and unaware. But fairy tales fall silent in the cold night air. You were a storm I be to stay. Lightning love that slipped away. Spoken real, smiled in rain. I kept dancing through your pain. Like that slipp smiled in rain. I kept dancing through your [Music] pain.
All right. Now, instead of pop rock, here's another example where the genre is J-pop EDM. And then I pasted some random Japanese lyrics from Chachi PT. Let's hear what this sounds [Music] like.
[Music] Fore speech. [Music] know [Music] me there.
[Music] Now notice that throughout the lyrics I have certain tags like verse one and then pre chorus and then chorus and then we also have a drop and then a synth. solo and you can kind of hear all these separate sections in the song. So these metatags gives the AI more direction on how to structure the song. It's really important that you add these keywords so that you get consistency with the verses and chorus. You often want it to repeat the same melody, right? Plus, you also want the chorus to be more exciting and more climatic than the verse. So these tags are really important.
Now, in addition to these tags, you can also do stuff like buildup or intro or outro or bridge. These are just a few examples that I have found to work well, but there might be other metatags that are also really useful. In fact, if you figure out any more, welcome to share these in the comments below.
So, for example, here's another generation where I added guitar solo between the verse and the chorus. And here is what we get.
Creed veins lost in echo of flames.
[Music] Here's another cool trick you can do in your lyrics. So if you add words in parenthesis at the end of the line, usually it actually makes that part echo. So notice here for example in the chorus I have sky in parenthesis and then in the next line I have I repeated twice and then in the next line I have fly. So if I jump to the chorus and play that for you, let's hear what that sounds like.
We're going to soar, baby, you and I. Drop the base, let the rhythm fly. Feel the heat. And don't ask [Music] why.
And there you go. Notice how it's kind of echoing the words in parenthesis.
Here's another tip in terms of writing your lyrics. So if you have some abbreviations like RTXGPU, make sure to actually space out each letter. So for example, you can add a space between each letter like this. Or you can also add hyphens to each letter like this. Or you can add dots to each letter just to make sure each letter is spaced out and it's actually going to read out all the letters. And then finally for 5090 here instead of using numbers it's best to actually type out how it should say these numbers. So in our case we want to refer to this as 5090. So here we have two verses. For the first verse this is what you should not do. So I do not expect it to sing these parts correctly. And then for the second verse that's where I separated the letters plus I specified how it should say the number. So it should sing this a lot more accurately. Let's hear both verses.
[Music] Boot it up. Let's fly through the view. Wondering dreams on an arc goo frame so fast we're breaking the sky. Nash love like a vessanded high. Boot it up. Let's fly through the view. Rendering dreams on an GPU. Frame so fast. We're breaking the sky. Next in love like a 5090 high. Bit by bit, we're building the vibe. Voltage rising. We're so alive. No lag, no cap, just light and sound. In this digital love, we're never powered down.
[Music] All right. Well, we've gone over some tips and tricks on how to format your lyrics. Let's also go over some tips and tricks for the tags.
So in general, I find that only specifying the genre would work. So like rock or pop or orchestral or EDM, trans, synth, wave, etc. Make sure you don't actually put all of these in one prompt or it's going to be really confusing. It's really hard to mix and match completely different genres together.
Now, if you want to specify the gender of your singer, you can simply write male singer or male vocalist or female vocalist or female singer. Certain words like upbeat or energetic or emotional, these also tend to work pretty well. However, here are some tags that do not work. If you write in the style of someone, it's not going to work. So, if you write in the style of Taylor Swift, this isn't actually going to generate a song that's like country pop in her style. Or if you do like the Beatles, for example, I found that it doesn't actually generate a song in the style of the Beatles. So, this doesn't work. And then specifying the BPM also doesn't really work. I tested this several times and I actually got a metronome to compare the BPM of the song with the specified BPM and it's not actually correct. However, you can kind of use this tag to dictate the pace of the song. So, for example, while setting a song to BPM 180 isn't actually going to give you a song with BPM of 180, it is going to be faster than if you set a song with BPM of like 60, for example. So, you could use this to roughly set the speed of your song.
Another thing that I tried out which doesn't really work is setting the key. So you can't really do like a minor key something like that or G major for example or in the key of D minor it doesn't actually give you the correct key and then finally time signature also doesn't really work so even if I put in 34 time or something like that it's not actually going to give me a song in 34 time at least 70 to 80% of the time this doesn't really work so for the tags it's mostly good for specifying the genre or instruments or mood that you want in the song.
All right. Now, instead of lyrics, if you want to generate a completely instrumental song, you can just put instrumental in square brackets like this. So, let's try this out. I'm going to put synth wave over here just to make this a bit faster. I'm going to set this to 20 seconds. And let's click generate and see what that gives us.
[Music] [Music] Instead of synth wave, here's an example of bluegrass. And also instead of instrumental, you can also just write inst and it would also generate an instrumental song. For this one, I'm going to just set it to 15 to make it even faster. And then click generate. And here's what we get.
[Music] or instead of blueg grass, here's an example of kawaii bass. Let's hear what that sounds like.
[Music] Here's an example of lowfi [Music] hiphop. I don't know about you, but it doesn't really sound like lowfi or hip-hop. So for instrumentals, I find that it works really well for some genres like rock or bluegrass, country, synth wave, retro wave, trans, future bass, kauawaii bass, those are pretty good. But for other genres like classical music or orchestral music or ambient music, it doesn't do so well. But note that this is kind of the same with the other tools like Suno or Udo or Refusion. They work very well at generating some genres, but not so well for others.
All right. Next, I want to show you a really cool feature called audio to audio. So, if you click this, you can upload a reference track for it to generate the style of. So, for example, I'm going to upload the first like 40 seconds of a song which I generated with Refusion. Let me play that for you really [Music] quickly. Stay true. Don't change. You taught me everything about keeping faith. Now I barely recognize the things you say. The person you became. Was it worth it in the end? Was it worth it in the end?
[Music] That song was stuck in my head for a few days by the way. Anyways, here we have a slider to adjust how much influence we want this reference audio to have on our generation. Usually, even the default value of.5 would be too high. And if you drag this to like 6 or 7, your generation is going to sound pretty much like the reference audio. So I tend to find that the range of 2 to.3 works the best here. Let's try 2. And then for the tags I'm going to try to describe this song which is like pop uplifting and female vocals. And then for the lyrics I'm just going to paste in some lyrics which I generated with chat GPT. And that's pretty much it. Let's click generate and see what that gives us.
All right here's what we get.
[Music] Woke up to the sound of doubt. Whispers trying to pull me down. But I've been through storms before and I'm still standing at the door. I'm going to shine anyesame.
[Music] [Music] Very nice. You can see that it sounds really similar to the reference audio. The singer sounds the same. I think the overall key and instrumentals also sounds like the reference track. So, this is a really useful tool. If you want to generate a new song in the style of an existing song, you can use this audioto audio feature. But note that again, this slider is super important. Make sure you set it to a lower value. Otherwise, it's going to sound way too similar to your reference song.
Now, I noticed an error here. Let me try to find it. So here it's kind of pronouncing an extra word here. So let's repaint this section only. I'm going to write something like you can always try to dim the flame just to fill in some syllables here. And then let's try to find the start and end of this line. So it starts at 36. And it ends at 40. So let's repaint 36 to 40. And then for the source, yes, we are going to use this source over here, which is our text to music generation. Or you can also upload a song here to edit. But I'm just going to use text to music. And then click on repaint.
All right. Here's what we get. Notice I added this extra word always over here. To save you time, I'm just going to skip to the chorus. still standing at the door. I'm going turn gray. You can't always try to dim the flame. And there you go. It magically changed the lyrics wherever you want to impaint this. One more thing I forgot to mention is that this variance slider is really important. This basically determines how much you want to change the impainted area. If you feel like it hasn't really changed the song, you can try to increase this variance amount to change the area even more.
All right. Next, let's also go over some of these tabs over here. So, first, this retake tab basically regenerates the song that you generated above, but it adds some difference to it. So, that's what this variance slider is about. So if you drag this to a lower value like 0.1 or 2 for example, it's going to regenerate this song. It's going to keep most of the elements the same, but there's going to be some subtle differences. Whereas if you drag this value higher and higher, it's going to add even more differences to the song. So for example, if this is the original song, let me play this for you first.
Neon lights they flicker bright. City hums in dead of night. Rhymes pulse through concrete veins.
All right. So if that is the original song and if we retake it with a variance of 2, let's hear what that would sound [Music] like. Neon lights they flicker bright. City hums in dead of night. rhythms pulse through concrete veins lost in echoes of refra.
So notice that it's a bit different from the original song. Now let's set the variance even higher to 4 and hear what that sounds like.
Neon lights they flicker bright. City hums in dead of night. Rhythms pulse through concrete veins lost in echo of reframes.
So, as you can hear, it sounds way more different than the original song. So, basically, use this retake setting if you want to regenerate your song, but add in some differences.
And then for repainting, we've gone over that before. It's where you can edit just a specific section of the song. And you would specify the start time and the end time of where in the song you want to edit over here.
And then for this edit tab, here's what it does. It's also super useful if you want to get the person to sing different lyrics, but keep the same song. So here I've already generated a song. The genre is acoustic pop emotional. Let's hear what this sounds like first.
on my face. Same old coffee, different kind of date. Scrolling through the memories we made, trying to find a reason why you walked away. But I won't let it break me down. I'll paint a smile, wear my crown.
[Music] All right. So, let's say I want to get her to sing out just a few words differently, but keep the rest of the song the same. Well, on this edit tab, I can basically copy the lyrics over here. And let's switch up some of the words. So, instead of day, I'm going to write way. Instead of why you walked away, I'm going to write why you couldn't stay. And then instead of break me down, I'm going to write break me now. So here we've made some subtle changes to some of these lyrics. And then down here, I'm going to select only lyrics to make sure it only switches out the lyrics that I've edited, but it doesn't affect the rest of the song. And then for the rest of the settings, I can leave it as is. Down here, I'm going to select text to music because yes, I want it to refer to this song which we just generated. And then after that, let's click edit and see what that gives us.
All right, here's the final song. Notice that it's exactly the same as the initial song, but it's going to sing our edited lyrics instead.
[Music] of wait. Scrolling through the memories we made, trying to find a reason why you couldn't stay. But I won't let it break me now. I'll paint a smile.
[Music] And there you go. So that is this really useful edit feature.
And then finally we have this extend tab. This is pretty self-explanatory. So this basically extends the song that you generated above over here. If you want to extend this by 30 seconds from the right, then you would select this or you can also increase the length that you want to extend. Or instead of extending this to the right, if you want to extend the song to the left, then you can also adjust this slider. And then for the extend source, if you select text to music, it's just going to be this one here. Or if you click upload, you can also upload a song over here for it to extend.
And that's pretty much it. That sums up all the features that you can do in this platform. It's a really powerful tool, and it's completely free and open source. So next, let's actually go over how to download and use this offline for unlimited times on your computer.
So here is their official GitHub repo, which I'll link to in the description below. Notice that if you scroll down here, it says the minimum VRAM requirement is 8 GB. So, this is very accessible to many people. And I'm sure because this is open-source, the community is going to quantize or compress this even further to potentially make this work with even lower VRAM. But note that for now, at least on the official repo, the minimum requirement is 8 GB. And note that this doesn't have to work with an Nvidia GPU. You can even get this to work with a MacBook M2. By the way, they also have a Comfy UI integration. So, click on this if you want to use this for Comfy UI. But for this video, to save you the trouble of downloading Comfy UI and working with all these nodes and noodles, I'm just going to go over how to download and use their native interface.
So, the first step is we need to get clone this repository, which requires that you have Git installed on your computer. If you don't, here's how to install it. If you already have Git installed, feel free to skip to the next section. So, all we got to do is download the latest release for whatever operating system you're using. So, I'm using Windows, so I'm just going to click on download for Windows. I'm running 64-bit, so I'm going to click on this to download. And it's now downloading this .exe file. So, once that's completed, all we got to do is open that .exe file and then follow the steps. So, I'm going to click on next. I'm just going to go with the default install location, which is program files/git. So, I'll click next for that. And then I'm just going to leave this at the default. And then I'm going to click next again. And click next. Here we're just going to use the default settings for all of these. There's a lot of settings that you need to go through. So I'm just going to click next for all of these. All right. And then it should go ahead and install all the files. So this might take a few minutes. Perfect. So now we have Git installed.
All right. So assuming you do have Git installed on your computer, simply navigate to where on your computer you want to install this. So let's say I want to install this on my desktop. I would simply open up my desktop and at the top here type in cmd to open my command prompt within my desktop folder. And then we just need to copy this line to get clone this aep repository. So let's press enter. And then afterwards on our desktop you should see this new folder called a step which if you open it it should contain all the files and folders that you see in this GitHub repo.
All right, the next step is to change the directory into the astep folder because in our command prompt right now we are still in desktop. So I'm going to copy this line and paste it in here to change the folder to a step. So after I press enter, note that we are now within this aep folder which we just cloned.
All right, the next step is we do need to have to create a virtual environment. So if you don't have installed, here is how to install it. If you already have installed, feel free to skip to the next section. Now, I'm just on Anaconda.com. And actually, what I'm going to do is install Minionda. This is a minimalist version of Anaconda. If you install the full Anaconda, it installs a lot of packages and dependencies that you might not need. This just takes up more room on your computer, and of course, the installation time is a bit longer. But with Minionda, it's just a barebones package. And you can always install additional packages and dependencies afterwards. So I'm going to click on latest Minionda installer links by Python version. And I'm using Windows, so I'm going to install one of these. Now, for free and open source AI tools, usually they do not support Python 3.12, so it's better to install the Python 3.11 version. So I'm going to click on this, which should download an exe file to your computer. Once it's finished downloading, simply doubleclick on this and then follow the steps to complete the installation. So, I'm going to click next and then agree. And then let's set this to all users. I'm going to go with the default destination folder. And then I'm going to check this as well. Clear the package cache upon completion. This just gives you back some more disk space without affecting functionality. All right. Once that's completed, let's click next. And then we are finished.
Now, we aren't done yet. So, if you open up the command prompt and you type in-- version, you're still going to see that is not recognized. This is because we haven't added Anaconda to our path yet. So, let's exit out of this. And then to add it to our path, we simply search for this function, edit the system environment variables. We're going to click on this and then click on environment variables and then click on the one that says path and then click edit. And here's where you add in the path of Anaconda. So it depends where you installed Anaconda. For me, I installed it in program data. So it's going to be in program data/min. And then if I double click on scripts, you can see that is here. So this is the folder we want to paste in. So I'm going to right click on this and then copy as path. And then back in the environment variables window, I'm going to click new and then paste in the path here. And then click okay. And then okay. And then okay again. Now if you open up command prompt again and type in- version you should see that we are running 24.5.0. So this shows that we have successfully installed Anaconda.
All right assuming you do have installed. The next step is to just use to create a new virtual environment called a step. And this is going to use Python 3.10. So let me just copy this line and then paste it in here and press enter. And while this is creating a new environment, if you're new to this, here's the point of creating a virtual environment. Think of it as like a separate hard drive on your computer that houses all the packages and dependencies that are required for ACE step. And you want to download and house everything in a separate environment so that it doesn't conflict with existing libraries and dependencies on your computer.
After we have created the virtual environment, the next step is to activate the virtual environment. So I'm going to click on this line and then paste it in here. So it's going to use to activate the environment we just created which is called ace_step. And then if we press enter, notice that we now have the environment name in parenthesis at the start of every line which signifies that you are now in your virtual environment.
All right. So we've covered this option. The next step is to install all the dependencies. So if you are using Windows with an Nvidia GPU, which I am, you need to run this line. So let me copy this. And then within our virtual environment, I'm going to paste it in here and press enter. And so this is going to download PyTorch and other dependencies which are around 2.8 GB in size. So this is going to take a while depending on the speed of your internet.
All right. If you see this line again with no error messages, then that means you have successfully installed PyTorch. Now the next step is to pip install a step and its core dependencies. So let's copy this line and then simply paste it in here and press enter. So again, it's going to proceed to install all the packages and dependencies that are required to run this. And it's going to take a few minutes depending on your internet.
All right. And after installing this long list of dependencies, if you see this line with no error messages, then you have successfully installed a step. So we can now proceed with running this. So, let me just exit out of this command prompt and show you how to start this up from scratch. So, all you need to do is go into your ASEP folder, wherever you downloaded it, and then at the top, type in cmd to open up this folder within command prompt. And then we simply need to type in activate and whatever you named your virtual environment. In our case, it's a step. So, I'm going to type this in and then press enter. So you should see that we are now within our virtual environment. The final step is to run this line of code apep-ort7865. So I'm just going to copy this line and then paste it in here. Now the first time you run this, it might take a few minutes, but eventually you're going to see this line running on local URL. And all you need to do is hold control and click on this link and it would open up this interface on your browser. Even though this is using your browser, note that this is completely offline. It's using this local address that you see over here.
Let's make sure everything works. So, I'm just going to paste in some random lyrics. To make this super fast, I'm going to set the duration to 15 seconds. For the tags, I'm just going to put pop. And then let's click generate. Notice the first time you click generate, it has to download some additional files, like the models, to actually generate the music. And this it looks like takes around 7 to 8 GB. So again, depending on your internet, you're going to have to wait a few minutes for this to download everything before it can actually generate your first song.
All right, after downloading all the models, it proceeds to generate the song. And here is what we get. Let's play this really quickly to make sure everything is working.
All nights they shimmer, they thrive. Electric pulses beat, they drive. My heart races just to survive.
Perfect. So there you go. That's how to install a step locally on your computer. Like I said, this is by far the best free and open-source AI music generator you can use right now. It's super flexible. There are so many capabilities for you to like edit songs or impaint songs or even do audio to audio. This is a super powerful tool. Props to them for open-sourcing this. And it's only going to get better. Let me know in the comments below what you think of this. And if you've had a chance to play around with it, what other cool or impressive generations were you able to come up with? And if you run into any errors while installing this, also welcome to copy and paste your error message in the comments below and I'll try to help you troubleshoot as much as possible.
By the way, if you want to win the exact laptop that I personally use to run these AI tools, it's a Dell Precision 5690 with an RTX 5000 ADA. And I'm partnering with Dell Technologies to give away the same laptop to a lucky winner. I'll have a link for the giveaway in the description below. Terms and conditions apply.