WEBVTT

NOTE Sentence-level transcript of https://www.youtube.com/watch?v=E_Txocq-Lrw

NOTE One cue per sentence. Cue ids are the line anchors on /transcripts/E_Txocq-Lrw.html. A cue ends where the next begins, or 2 s after its last word.

s1
00:00:01.309 --> 00:00:03.309
[music]

s2
00:00:12.480 --> 00:00:13.920
So, I am Todd Fischer.

s3
00:00:13.920 --> 00:00:14.799
I love the guitar.

s4
00:00:14.799 --> 00:00:16.320
That's one of my passions in life.

s5
00:00:16.320 --> 00:00:23.680
Uh, today I want to talk about uh this project I've been working on for a while here, effectively making my guitar speak.

s6
00:00:23.680 --> 00:00:28.160
Uh, but of course I want to start out with kind of framing it under this awesome premise.

s7
00:00:28.160 --> 00:00:31.679
You know, we've all been to live performances where like your mind was just blown.

s8
00:00:31.679 --> 00:00:32.719
It was awesome.

s9
00:00:32.719 --> 00:00:36.640
You know, the the first one I remember way back I was in high school.

s10
00:00:36.640 --> 00:00:41.120
I went to a Slipnot concert, so a little bit heavier music uh here in the Bay Area.

s11
00:00:41.120 --> 00:00:46.559
And I remember at some point the drummer was drumming a cool drum solo, and his drum set started raising up.

s12
00:00:46.559 --> 00:00:47.600
And I was like, "Whoa, that's cool."

s13
00:00:47.600 --> 00:00:49.680
And everyone got kind of excited, right?

s14
00:00:49.680 --> 00:00:54.559
And then halfway through the solo, his drum set started to go like this and tipping.

s15
00:00:54.559 --> 00:01:02.879
and his whole drum set was like on the wall while he was upside down playing his drum solo and everyone was just cheering like whoa this is so crazy mind-blowing

s16
00:01:02.879 --> 00:01:13.600
like whoa it was so so impactful right I still reme remember it today um fast forward probably about a year ago uh I went to New York to see the Stranger Things on Broadway

s17
00:01:13.600 --> 00:01:26.799
the the first shadow and it was really cool because the whole time I was there I was watching it and it felt like it was actually like a a Netflix episode but in real life and it was just like the effects that they did there was so so amazing.

s18
00:01:26.799 --> 00:01:41.840
I remember even one time at near the end there was a scene where somebody somebody was falling backwards and it was like a slow motion scene and it probably about a minute long the whole scene but just like the fact that like they they were able to produce that in real life but it looked like it was

s19
00:01:41.840 --> 00:01:45.360
a post-prouction slow motion scene just just mind-blowing.

s20
00:01:45.360 --> 00:01:46.479
So it's like well that's cool.

s21
00:01:46.479 --> 00:01:58.079
So given you everyone here's probably had some experiences with live performances in the past and I think it's really awesome just to like see the creativity uh that people can do with leveraging technology

s22
00:01:58.079 --> 00:02:00.000
in some creative way.

s23
00:02:00.000 --> 00:02:06.000
And so you know I'm thinking about all the projects that we have as engineers over the years where it's like hey that's a cool idea.

s24
00:02:06.000 --> 00:02:06.719
I'm going to write this down.

s25
00:02:06.719 --> 00:02:07.840
I have like a big giant list.

s26
00:02:07.840 --> 00:02:10.959
Anyone have a list of projects that maybe they'll get to?

s27
00:02:10.959 --> 00:02:11.280
Yeah.

s28
00:02:11.280 --> 00:02:12.640
So it all happens right?

s29
00:02:12.640 --> 00:02:22.879
Uh, and it's really awesome because the last 6 months or so with AI, uh, being able to, you know, push us forward with some of these projects, it's just really cool to see where we can take all these projects.

s30
00:02:22.879 --> 00:02:31.360
So, so part of, uh, my goal today is to inspire you guys to find whatever project you're passionate about, go start building it because it's super easy now with AI.

s31
00:02:31.360 --> 00:02:32.560
I get easier with AI.

s32
00:02:32.560 --> 00:02:42.160
I know sometimes there's caveats, but but in general, uh, I I want to have you guys leave this session being inspired to go build whatever that cool thing is for you personally.

s33
00:02:42.160 --> 00:02:48.080
that's gonna, you know, help you to learn stuff or maybe make a difference in the things that you're you're trying to figure out.

s34
00:02:48.080 --> 00:02:52.720
Uh, so I want to start off with framing this kind of in the realm of the guitar.

s35
00:02:52.720 --> 00:02:58.080
So the guitar acoustic guitar has been around for several years, several thousands or hundreds of years, sorry.

s36
00:02:58.080 --> 00:03:02.239
Um, and at some point somebody said, "Hey, I'm going to put a pickup on a guitar.

s37
00:03:02.239 --> 00:03:04.239
I'm going to plug it into a speaker."

s38
00:03:04.239 --> 00:03:05.840
And now we have rock and roll.

s39
00:03:05.840 --> 00:03:06.959
We're going to make it super loud.

s40
00:03:06.959 --> 00:03:08.239
That was pretty awesome.

s41
00:03:08.239 --> 00:03:12.720
And then of course we have a lot of people getting these stomp boxes, these these effects pedals.

s42
00:03:12.720 --> 00:03:13.680
We put them all together.

s43
00:03:13.680 --> 00:03:15.040
We have really awesome sounds.

s44
00:03:15.040 --> 00:03:17.519
You really famous people have a lot of these.

s45
00:03:17.519 --> 00:03:32.319
Uh and then at some point Peter Peter Frampton came along and said, "Hey, what if we get the sound of the guitar, put it through an actual hose, like a physical hose, put it in my mouth, and then basically play the guitar sound in my mouth and inform some sort of words.

s46
00:03:32.319 --> 00:03:35.280
So that's pretty awesome that that's known as the talk box.

s47
00:03:35.280 --> 00:03:39.920
And then in the last couple decades we have a lot of progress made with software emulation.

s48
00:03:39.920 --> 00:03:53.920
Uh you think of you know protools you think of logic of uh fruity loops there's a lot of software even to the point where all the effects are in software now there is the argument made hot take that maybe you don't need all those physical effects pedals anymore.

s49
00:03:53.920 --> 00:04:03.040
So so there's that question right and then of course looking forward it's what is that next evolution of the guitar uh with AI in the picture.

s50
00:04:03.040 --> 00:04:07.200
So, with that said, I want to take you back several years ago, Halloween time.

s51
00:04:07.200 --> 00:04:09.920
I was passing out candy, bunch of trick-or-treaters.

s52
00:04:09.920 --> 00:04:11.280
You know, it got kind of boring.

s53
00:04:11.280 --> 00:04:15.840
So, I was like, "Hey, what if I go and actually bring my guitar out with my amp and just play?"

s54
00:04:15.840 --> 00:04:22.880
Uh, so for the past what, 10 or years or so, I've actually been playing guitar on Halloween, passing out candy, and it's kind of fun.

s55
00:04:22.880 --> 00:04:27.440
Uh, and then fast forward probably three years ago, I decided to dress up as Eddie Mson.

s56
00:04:27.440 --> 00:04:28.880
Anyone know Eddie Mson?

s57
00:04:28.880 --> 00:04:31.280
Stranger Things guitar player guy.

s58
00:04:31.280 --> 00:04:32.320
So, pretty awesome guy.

s59
00:04:32.320 --> 00:04:33.280
So, I dressed up as him.

s60
00:04:33.280 --> 00:04:34.560
I was like, "This is going to be so fun.

s61
00:04:34.560 --> 00:04:36.160
I can play the music with him."

s62
00:04:36.160 --> 00:04:36.479
Whatever.

s63
00:04:36.479 --> 00:04:40.800
And you kind of go the Oh, hold on.

s64
00:04:42.080 --> 00:04:42.479
Hold on.

s65
00:04:42.479 --> 00:04:44.880
Wait a minute.

s66
00:04:45.600 --> 00:04:48.160
Technical difficulties.

s67
00:04:49.199 --> 00:04:51.478
All right, there it goes.

s68
00:04:51.478 --> 00:04:53.478
[music]

s69
00:04:56.160 --> 00:04:58.639
So, a bunch of little Stranger Things awesomeness, right?

s70
00:04:58.639 --> 00:05:03.680
Uh, but figured out, hey, what if there was like some more stuff I could put in this whole experience.

s71
00:05:03.680 --> 00:05:11.360
And so I decided to go and build a little app that would actually paint the Stranger Things alphabet on my garage door just because it's fun, right?

s72
00:05:11.360 --> 00:05:14.800
Uh, and so let me just show you a quick example of how this worked.

s73
00:05:14.800 --> 00:05:18.720
So effectively, make sure I have the mic permission.

s74
00:05:18.720 --> 00:05:24.320
Whenever I play a note, it would go and communicate whatever lights.

s75
00:05:24.320 --> 00:05:30.639
And I even had it to where I could actually set custom messages such as happy Halloween, all that fun stuff.

s76
00:05:30.639 --> 00:05:33.840
It was it was overall pretty fun just to kind of mess with that, right?

s77
00:05:33.840 --> 00:05:42.400
So once again, you know, whatever I type in there, I could actually spell whatever and and very much a cool nod to Stranger Things.

s78
00:05:42.400 --> 00:05:46.320
But it kind of got me thinking like what is the next evolution of this project?

s79
00:05:46.320 --> 00:05:50.960
And I settled on this idea of like, hey, how hard would it be to make my guitar speak?

s80
00:05:50.960 --> 00:05:51.919
It sounds easy.

s81
00:05:51.919 --> 00:05:53.199
Maybe, maybe not.

s82
00:05:53.199 --> 00:05:59.280
So, so today I want to share kind of my journey uh in this process and where kind of I'm at today.

s83
00:05:59.280 --> 00:06:03.360
Uh so looking around the different tools, there's a framework out there called Juice.

s84
00:06:03.360 --> 00:06:03.919
Really awesome.

s85
00:06:03.919 --> 00:06:06.560
For anyone building audio software, look into Juice.

s86
00:06:06.560 --> 00:06:07.759
It's it's pretty good.

s87
00:06:07.759 --> 00:06:15.199
Um and then of course there's a number of plugins uh sorry plug-in formats out there uh for your your digital audio workstation.

s88
00:06:15.199 --> 00:06:22.080
And for for those that are not aware, uh your DAW is effectively your IDE but for musicians and and music producers.

s89
00:06:22.080 --> 00:06:30.319
And then I I started with some text to speech stuff with Piper and some built-in Apple stuff and then some other really fun uh digital signal processing.

s90
00:06:30.319 --> 00:06:38.960
Uh so with that said, my first stab here was I want to get raw text so I could just type in whatever text I want uh push it through the text to speech

s91
00:06:38.960 --> 00:06:44.319
uh get the audio clip and then whenever I play a note on the guitar I want to go and play that back.

s92
00:06:44.319 --> 00:06:46.639
So let's go see how that works.

s93
00:06:46.639 --> 00:06:52.160
So, switching over to my Logic Pro here, and this is the plugin I made.

s94
00:06:52.160 --> 00:06:56.319
So, it's just like any other plugin in Logic where you just plop it in there.

s95
00:06:56.319 --> 00:06:59.120
It's just, you know, chaining all the effects together.

s96
00:06:59.120 --> 00:07:02.479
And so, this is what I came up with.

s97
00:07:02.479 --> 00:07:04.160
Developers.

s98
00:07:04.160 --> 00:07:06.160
So, it's playing it.

s99
00:07:06.160 --> 00:07:08.720
Pretty awesome, right?

s100
00:07:09.199 --> 00:07:11.360
Kind of reminds me of something, right?

s101
00:07:11.360 --> 00:07:12.000
Start clapping.

s102
00:07:12.000 --> 00:07:13.599
Everyone start clapping.

s103
00:07:13.599 --> 00:07:14.479
Developers.

s104
00:07:14.479 --> 00:07:15.440
Developers.

s105
00:07:15.440 --> 00:07:18.800
developers, developers, developers.

s106
00:07:18.800 --> 00:07:19.199
Awesome.

s107
00:07:19.199 --> 00:07:19.759
Thank you.

s108
00:07:19.759 --> 00:07:20.639
That's pretty awesome.

s109
00:07:20.639 --> 00:07:21.919
Uh, you guys are great.

s110
00:07:21.919 --> 00:07:25.680
Um, so I got it to where it's playing an actual audio file.

s111
00:07:25.680 --> 00:07:26.400
That's pretty awesome.

s112
00:07:26.400 --> 00:07:30.880
But it turns out, you know, in English or in any languages for that matter, there's more than one word.

s113
00:07:30.880 --> 00:07:34.400
So the next kind of evolution, it's a little bit chatty.

s114
00:07:34.400 --> 00:07:39.280
The next evolution there is let's actually go and slice it per word now.

s115
00:07:39.280 --> 00:07:41.919
So I got to the point where it's playing now.

s116
00:07:41.919 --> 00:07:43.680
It's going to slice per word.

s117
00:07:43.680 --> 00:07:45.599
Look at me.

s118
00:07:45.599 --> 00:07:47.680
I can speak.

s119
00:07:47.680 --> 00:07:49.680
Look

s120
00:07:50.560 --> 00:07:51.680
me.

s121
00:07:51.680 --> 00:07:53.199
I can speak.

s122
00:07:53.199 --> 00:07:54.800
So now it's speaking words.

s123
00:07:54.800 --> 00:07:56.479
And that's pretty awesome, right?

s124
00:07:56.479 --> 00:08:03.840
Uh but it turns out that uh as we speak, there's a number of challenges in how we automatically slice words.

s125
00:08:03.840 --> 00:08:06.560
So I looked into this thing called energy gap segmentation.

s126
00:08:06.560 --> 00:08:14.319
The general idea here is if you look in any waveform over here, we see that here's a bunch of of words that we're speaking, right?

s127
00:08:14.319 --> 00:08:18.240
Uh the idea there is there's typically silence in between words.

s128
00:08:18.240 --> 00:08:22.240
So let's just cut it whenever the decibb are very much close to zero, right?

s129
00:08:22.240 --> 00:08:30.720
Uh but the issue with that is there's actually sometimes when you know as I'm speaking right now, for example, uh there's actually no silence in between some of my words.

s130
00:08:30.720 --> 00:08:34.800
So it gets a little bit challenging to where it's not 100% foolproof, right?

s131
00:08:34.800 --> 00:08:39.279
So beyond that, I looked into this thing called sority peak syllab syllabifier.

s132
00:08:39.279 --> 00:08:40.479
That's a hard word to say.

s133
00:08:40.479 --> 00:08:46.959
Effectively identifying the syllables of the audio signal and identifying that there's vowels in here.

s134
00:08:46.959 --> 00:08:48.720
Vowels typically lead to syllables.

s135
00:08:48.720 --> 00:08:49.920
That's kind of the idea.

s136
00:08:49.920 --> 00:08:58.720
So I said, "Okay, let's take the senority peak, add it to the uh the energy gap, and figure out if we could just make that work automatically."

s137
00:08:58.720 --> 00:09:00.959
So with that said, made it kind of work.

s138
00:09:00.959 --> 00:09:02.560
So let's just play this one.

s139
00:09:02.560 --> 00:09:06.080
Thank you for letting me Nope.

s140
00:09:06.080 --> 00:09:06.480
Oh,

s141
00:09:06.480 --> 00:09:12.880
here it feels so good.

s142
00:09:13.600 --> 00:09:23.040
Get out of my target case once in a while.

s143
00:09:23.040 --> 00:09:23.839
So, there you go.

s144
00:09:23.839 --> 00:09:25.440
It's working pretty well.

s145
00:09:25.440 --> 00:09:27.120
Not quite as good as I want to.

s146
00:09:27.120 --> 00:09:36.320
So, long story short, uh I settled on just the ability to go and actually I could drag this and manually edit some of these uh uh segments in here.

s147
00:09:36.320 --> 00:09:37.920
So, worked okay, right?

s148
00:09:37.920 --> 00:09:43.839
Um but moving on, you know, with the spirit of evolving the thought, evolving the project, right?

s149
00:09:43.839 --> 00:09:46.959
It's like, okay, we're we're having the AI say stuff.

s150
00:09:46.959 --> 00:09:49.600
That's great, but what if we could actually make it sing?

s151
00:09:49.600 --> 00:09:51.839
Let's take it to the next step because this is music.

s152
00:09:51.839 --> 00:09:52.720
Why not, right?

s153
00:09:52.720 --> 00:09:54.640
Uh so, looked into pitch detection.

s154
00:09:54.640 --> 00:10:05.279
And for those that are not aware, uh, as you hear any any noise out there, there's typically multiple frequencies going on at any given time, you know, you think of when you play the the C key on the piano.

s155
00:10:05.279 --> 00:10:12.320
Uh, there is definitely a fundamental frequency or the the kind of the the one that we identify as the note, but there's a bunch of other frequencies.

s156
00:10:12.320 --> 00:10:16.800
So, we needed a way to go and figure out like how do we detect that fundamental frequency?

s157
00:10:16.800 --> 00:10:21.360
So, when I press something on the guitar, how do I translate that into an actual note?

s158
00:10:21.360 --> 00:10:24.640
Uh, and then I found this uh, yin pitch algorithm.

s159
00:10:24.640 --> 00:10:27.120
Basically what it does is it detects the pitch.

s160
00:10:27.120 --> 00:10:29.120
I won't get into all the details, but look it up.

s161
00:10:29.120 --> 00:10:33.440
It's kind of a fun uh, really cool way of detecting the pitch.

s162
00:10:33.440 --> 00:10:36.480
Uh, but effectively what I do is I play the guitar.

s163
00:10:36.480 --> 00:10:39.200
Uh, I detect the the pitch.

s164
00:10:39.200 --> 00:10:44.240
I I make what's effectively a pitch saw or aka a synthesized note.

s165
00:10:44.240 --> 00:10:51.200
Uh so for those that are not familiar with how audio works on the the computer, you think of all the e electronic music, all that stuff.

s166
00:10:51.200 --> 00:10:54.000
Uh that is basically uh a synthesized note.

s167
00:10:54.000 --> 00:11:00.240
We have ADSR which effectively are the levers to figure out how to actually make the note sound in different ways.

s168
00:11:00.240 --> 00:11:04.560
Uh and then so basically we get the pitch note or the syn synthesized note.

s169
00:11:04.560 --> 00:11:08.160
Uh we then push it through uh the the voice clip effectively.

s170
00:11:08.160 --> 00:11:09.839
So think of the talk box.

s171
00:11:09.839 --> 00:11:13.120
We're kind of filling up the cavity of the talk of the voice that is.

s172
00:11:13.120 --> 00:11:16.079
and we push it through a vocoder and it should sing.

s173
00:11:16.079 --> 00:11:18.399
So that's kind of the idea, right?

s174
00:11:18.399 --> 00:11:23.440
So with that said, let's go ahead and jam out a little bit because I have a guitar and it's fun.

s175
00:11:23.440 --> 00:11:28.560
So get back to Logic here.

s176
00:11:30.880 --> 00:11:32.399
Uh so I'm going to play some chords.

s177
00:11:32.399 --> 00:11:41.040
Uh I originally was gonna uh play a song that is very much related to the talk or the the title of my talk, While My Guitar Gently Speaks.

s178
00:11:41.040 --> 00:11:46.880
But because it's going to be posted online, I don't want to muddy up the waters with any copyright things.

s179
00:11:46.880 --> 00:11:51.120
So, I will play some chords that may or may not sound similar to a famous song.

s180
00:11:51.120 --> 00:11:53.120
So,

s181
00:11:59.853 --> 00:12:01.853
[music]

s182
00:12:19.040 --> 00:12:25.360
Hey, hey, hey.

s183
00:12:31.120 --> 00:12:32.480
So that's the backing track.

s184
00:12:32.480 --> 00:12:39.360
So let's go ahead and have some AI speaking on top of it.

s185
00:12:41.920 --> 00:12:44.959
I'm here.

s186
00:12:46.959 --> 00:12:48.079
No. Hold on.

s187
00:12:48.079 --> 00:12:49.040
Technical difficulties.

s188
00:12:49.040 --> 00:12:51.519
Let's try that again.

s189
00:12:53.279 --> 00:12:54.800
Live demos always the best.

s190
00:12:54.800 --> 00:13:02.720
I'm here at this con friends.

s191
00:13:03.388 --> 00:13:05.388
[laughter]

s192
00:13:09.519 --> 00:13:11.200
All right, technical difficulties again.

s193
00:13:11.200 --> 00:13:12.639
So, sorry for that.

s194
00:13:12.639 --> 00:13:16.639
But let's just run through it and see what happens.

s195
00:13:19.109 --> 00:13:19.680
[music]

s196
00:13:19.680 --> 00:13:23.694
Con friends

s197
00:13:23.694 --> 00:13:23.920
[music]

s198
00:13:23.920 --> 00:13:25.360
that speak.

s199
00:13:25.360 --> 00:13:30.480
I'm the guitar that can speak.

s200
00:13:30.959 --> 00:13:32.160
So

s201
00:13:32.160 --> 00:13:32.639
awesome.

s202
00:13:32.639 --> 00:13:33.760
So there you go.

s203
00:13:33.760 --> 00:13:38.240
Some bugs to work out, but overall we are able to to say words on top of this.

s204
00:13:38.240 --> 00:13:44.720
And for what's worth, I'm trying to mix the uh the the synthesized note with this clarity lever right here.

s205
00:13:44.720 --> 00:13:49.839
So balance or mixing the the synthesized note with the actual voice that the AI is giving.

s206
00:13:49.839 --> 00:13:51.839
Uh so so that worked pretty good.

s207
00:13:51.839 --> 00:13:59.760
Um but there's also this other question, you know, given that uh when you speak it's typically conversational.

s208
00:13:59.760 --> 00:14:01.760
What if I could take this to the next level?

s209
00:14:01.760 --> 00:14:06.639
And what if we actually had this microphone right here where I could speak into the mic?

s210
00:14:06.639 --> 00:14:09.040
It would then respond on the guitar.

s211
00:14:09.040 --> 00:14:13.600
So the way that I accomplished this is speaking to the mic used speech to text.

s212
00:14:13.600 --> 00:14:18.800
a whisper uh put that into raw text, run a local model on my computer.

s213
00:14:18.800 --> 00:14:21.760
It doesn't really matter what LLM, just any local model.

s214
00:14:21.760 --> 00:14:26.560
Have a conversation coming and then from that output go and plop it on the guitar.

s215
00:14:26.560 --> 00:14:29.680
So, let's see how this works.

s216
00:14:34.560 --> 00:14:38.639
Anyone have a question you want to ask my guitar?

s217
00:14:39.760 --> 00:14:41.760
Anybody?

s218
00:14:42.000 --> 00:14:43.279
What is reality?

s219
00:14:43.279 --> 00:14:45.760
Let's do it.

s220
00:14:46.639 --> 00:14:49.120
What is reality?

s221
00:14:50.240 --> 00:14:56.240
So, it's thinking going through the LLM things and let's see what it says.

s222
00:14:56.240 --> 00:15:03.255
That's quite a question to start with.

s223
00:15:03.255 --> 00:15:04.399
[laughter]

s224
00:15:04.399 --> 00:15:18.000
How does your music help you understand that elusive concept to real be right now?

s225
00:15:18.000 --> 00:15:19.360
So, yeah, very existential.

s226
00:15:19.360 --> 00:15:19.920
I like that.

s227
00:15:19.920 --> 00:15:22.240
So, thank you for that suggestion there.

s228
00:15:22.240 --> 00:15:22.959
So, there you go.

s229
00:15:22.959 --> 00:15:25.519
We have a choppy version, but but it is working.

s230
00:15:25.519 --> 00:15:26.880
So, so that's a win, right?

s231
00:15:26.880 --> 00:15:27.760
Uh, awesome.

s232
00:15:27.760 --> 00:15:29.199
And thanks for the claps, sir.

s233
00:15:29.199 --> 00:15:33.680
Um, but really like it's not quite singing yet, right?

s234
00:15:33.680 --> 00:15:37.680
So, moving on in this project, it's like how do I actually make it sing, right?

s235
00:15:37.680 --> 00:15:43.920
I found a lot of uh open- source options out there as far as uh uh recordings or or samples if you will.

s236
00:15:43.920 --> 00:15:45.680
There's a thing called vocal set out there.

s237
00:15:45.680 --> 00:15:50.880
They basically recorded a bunch of singers and I could use those audio files to go and do some fun stuff with them.

s238
00:15:50.880 --> 00:15:53.279
And effectively, I took those samples.

s239
00:15:53.279 --> 00:15:58.480
I used a project called World, which helps with things like pitch shifting and some other things.

s240
00:15:58.480 --> 00:16:05.040
and I'm able to then shift the the pitches of everyone singing on those audio clips and map it to the guitar.

s241
00:16:05.040 --> 00:16:08.720
Uh, this is a very heavy process and so I can't really do that live.

s242
00:16:08.720 --> 00:16:14.560
I have to effectively pre-bake that and then once it's already pre-baked, I could then go and jam out with it.

s243
00:16:14.560 --> 00:16:20.240
So, with that said, uh, let me go ahead and show that example here.

s244
00:16:24.000 --> 00:16:27.600
So, uh, because it takes so long, I actually just started with the vowel sounds.

s245
00:16:27.600 --> 00:16:31.040
So there's somebody singing all each of the five vowels.

s246
00:16:31.040 --> 00:16:34.399
And so we'll see how that sounds, right?

s247
00:16:41.279 --> 00:16:41.920
Kind of fun.

s248
00:16:41.920 --> 00:16:43.839
Kind of weird, but overall it's working.

s249
00:16:43.839 --> 00:16:46.160
It's It's closer to singing, right?

s250
00:16:46.160 --> 00:16:53.920
Uh so let's go ahead and throw that on top of all the chords over here, and let's see if we can make it sound decently well.

s251
00:16:53.920 --> 00:16:58.536
Oh, so we'll just play these chords again.

s252
00:16:58.536 --> 00:17:00.536
[groaning]

s253
00:17:15.199 --> 00:17:20.480
So, not quite your opera singer, but getting closer and and so I I think there's something awesome there.

s254
00:17:20.480 --> 00:17:36.720
Uh so effectively once again that is going through the whole synthesize process uh putting a sample shifting the pitch shift of the sample and then effectively mapping each fret or each note on the guitar to one of those samples that are pre-baked effectively right.

s255
00:17:36.720 --> 00:17:49.600
So with that said you know where do I want to take this next uh very much want to get into more of of the you know AI heavier options if anyone has any other ideas of how to make the guitar sing feel free to come up to me after.

s256
00:17:49.600 --> 00:17:50.799
I think it's pretty awesome.

s257
00:17:50.799 --> 00:18:00.400
Uh but more importantly, you know, everyone here going back to the the charge to go in and build some awesome, you know, side project, some passion project of yours, like what is that for you?

s258
00:18:00.400 --> 00:18:09.679
Go and build awesome things because nowadays with AI, we could build so many really cool things and time is typically not the the big time suck that that it once was, right?

s259
00:18:09.679 --> 00:18:16.482
So, with that said, uh be awesome or be good to each other and thank you very much.

s260
00:18:16.482 --> 00:18:18.482
[applause]