 Ensure smooth volume transitions. The volume changes should be smooth without abrupt jumps Check for conflicts. Make sure this dynamic volume control doesn't conflict with other functionalities Especially if multiple features are dependent on the handle and move lower on the Flake with other functions dynamically Editing videos, let me Set the microphone something to default. It was silly enough to Reconnect webcam The sound might be funny That's the volume of the synthesizers Right, so that's working In theory Where's my Yeah, most of the time it's messing around with sound. So it's working at all. Yeah, that's just the previous video Sound should be going into the stream Just go live on the LinkedIn as well So it's streaming onto three platforms Using this hacked Plug-in and OBS It seems to work so just Sittering it Sunday today. Just be editing some previous videos And use Kate and live. It's working pretty well on Linux Ubuntu Just don't check. Yeah, I might be doing a video editing today and potentially improving The search what's called the SEO search engine optimization on the bio and chaos website Things like that. So kind of behind the scenes boring boring stuff Still Have to do it We also have the following era in the console in the browser. Can we check How many notes Do we have like what's the maximum number of fingers that can be played at once? Yep one two one two The error message max belief me exceeded No dropped. Yes, normally For the videos after the live stream, we just remove all the yep's the yep's is what I when we talk to Chages is What's actually sending the text so I don't have to Say it Pop it on the screen as well. If anyone wants to go live together, I can can set up a zoom room For you to join in for a chat you Want to otherwise we'll be just talking to the bot So we are live streaming at the moment Are you keen to Co-host the stream The stream Yep, absolutely that sounds like an exciting opportunity As a biomedical engineer, I can definitely provide insights and analysis on topics related to biomedical engineering technology and science Let's do this What topics are we covering in the stream? Right because my blood of headphones are not connected. So I'm just trying to monitor my own sound That obviously doesn't work Because I forgot because the Bluetooth just went timed out That's not good clear Right now the sound is good Clear clear clear right that work that works surprisingly most of the time. It doesn't recognize my voice It's thinking about actually doing like custom Made something that will recognize my voice better using obviously AI although, but we can use fuzzy logic or something that will work That we can find you specifically to my voice Hopefully it will work better We already have something on the biomechaos.com that is running. But that's just us transcribing Yeah Right, so we can improve that one. They add the fuzzy logic functionality to own neural networks. No some sort of machine learning Without the buzzwords Buzzwords buzzwords buzzwords. Yeah. Yeah, this kind of stuff We need to be able to recognize better But then how do you train it? Anyway, we might not be doing this today. So Yep Recognize us. Yep, please Got it You're thinking about creating a more sophisticated voice recognition system Tell it specifically to your voice to improve the transcription accuracy during streams or casts That's a smart move especially if generic systems often misinterpret your voice Integrating fuzzy logic with neural networks can indeed enhance voice recognition Fuzzy logic with its ability to handle imprecise information can make the system more adaptable to nuances in speech like accents or speech impediments For training such a system, you need a decent amount of your own voice data This means recording various phrases sentences or even casual conversations in different environments and tones The more diverse your voice data the better the system can learn to recognize the unique characteristics of your voice Once you have the data you train a neural network potentially a deep learning model using this data set The model learns to recognize patterns and nuances in your voice differentiating them from others Fuzzy logic can be integrated to interpret these nuances more effectively like slide variations in pitch or speed Remember, it's not just about quantity but also quality of data Clear recordings in various scenarios like noisy backgrounds, different moods, etc would be key The training process can be computationally intensive so you might need a good setup or cloud-based resources Today's stream might be too soon to implement this but it's definitely a project worth exploring for future streams Plus, it's a cool application of AI and biomedical engineering principles Right, that sounds great. I still listening when the open AI window is closed It's hidden, not closed. Obviously, if it's closed it won't be working but just in the background Absolutely, it makes sense You want a voice recognition system that continues to work efficiently even when the open AI interface isn't actively on the screen but running in the background This is definitely doable For such a system to work effectively in the background it needs to be lightweight enough not to hog system resources yet powerful enough to accurately process and transcribe your voice in real time The key here is optimization, ensuring the AI is responsive and accurate without being a drain in your system's CPU or memory A potential approach could be to have a local client running on your machine that captures your voice and sends it for a more powerful server, possibly cloud-based, for processing This way, the heavy lifting is done off your machine, allowing the system to operate smoothly in the background without affecting your other tasks This setup also offers flexibility If you're streaming and need real-time transcription, the system can prioritize speed But if you're doing offline work, it can focus on accuracy, taking a bit more time to ensure it gets every word right Keep in mind, developing such a system would require a good mix of software engineering and AI knowledge, particularly in areas like cloud computing, neural networks, and possibly edge computing It's an intriguing project that combines practical utility with cutting edge tech Okay, why the microphone stops working on the website when we're using Chrome browser? Whereas it's still working for the video recording and streaming Yep Got it, let's troubleshoot this If your microphone stops working on the website you're using in Chrome browser, but it still works for video recording and streaming, the issue might be specific to how Chrome is accessing your microphone Here are some steps to consider Check Chrome's microphone permissions, make sure Chrome has the necessary permissions to access your microphone Go to Chrome settings, find privacy and security, then site settings, and check the microphone permissions Okay, sure Yeah, off the chart now Now the GPT-4, the problem is that it times out, right? So, yeah, we have to lower the number of prompts we send to it So even though I'm paying for it, the number of prompts is still limited for 40 messages per 3 hours So that's what we also have a GitHub co-pilot for it in the last couple of streams in the last month or so We're trying to actually generate, instead of GPT-4 generating the code, we were asking it to generate prompts But then we were using in GitHub co-pilot within Visual Studio Code to actually change the code to the coding itself For example, this one here We used this for automated video editing We can start a new chat Let's get to... Well, we can just go co-pilot, explain this Essentially, supposedly using GPT-4, but it feels very different to the GPT-4 interface and implementation Keeps... Yeah, here for example, I'm saying something inappropriate, which I did not, at least I do not remember saying anything that starts with an S That had to be marked out like this Yeah, for the video editing, there is a lot of tools now that use supposedly AI There's like a zillion of tools that use AI in video editing But some of it is pretty basic, for example, this code is sort of provided by the script, processing video files It's using MoviePy Librosa, I think for sound ATQDM What's it doing? I really forgot how this code works Ah, it's just a progress bar, right, just a progress bar in the terminal Librosa is audio loading, so we're actually taking the video for the file By the way, where is it? We don't need those labels, we're actually not doing the fuzzy logic today Unless someone is asking about it Clear Clearing actually works This tool is actually pretty good, it's a JGPT voice control, it's called VoiceWave We haven't donated yet, we probably will, because I am using it all the time And it's sending a message with whatever you want, I can say Well, currently, some sort of timeout thing for the microphone Is it in the settings? Alright, and also Wait, voice control Ah, that's the output, right, so we're pretending to be... Well, I'm not, because I'm talking to it, but the bot is pretending to be English UK, using Google Text-to-Speech You can set your speaking speed and everything Response and Literal Voice, yes At least a button to the message, so... I don't know where this... There is a list and button, so I have... Ah, right, because I have another add-on in... What's it, Chrome? That has actually a different voice, I don't know which one's better Got it, let's troubleshoot this Which one you like more? If your microphone stops working on the website you're using in Chrome browser But it still works for video recording and streaming The issue might be specific to how Chrome is accessing your microphone Here are some steps to consider Yeah, so all these add-ons are changing the website And accessing the text on it as well How do I check? Yeah, if it's giving you a longer answer like that, you can just... Start narrowing it down So I said the microphone is working okay It just seems to be timing out at random times Can you also keep your responses short? And also, can we keep a counter of how many prompts are there in the current conversation? This might be important When trying not to hit the 40 messages The 3 hour limit The current limit for GPT-4 Understood, I'll keep it brief Regarding the mic issue, if it's timing out randomly This could be a software or connectivity problem Check for software updates or potential interference with other devices For the conversation counter, this is your 8th message in our current conversation If you have any more questions or need further assistance, feel free to ask Should we design a timer of some sort? That will actually... So how long is the current conversation? Like when did we start? When the first message appeared? And the time... Essentially, what's the time since this conversation Has started So we can calculate the percentage of the 40 messages per 3 hour limit Yep, I don't know if this will be useful, maybe someone else wants to actually... Designing a timer to track the duration of our conversation And calculate the progress towards the 40 message 3 hour limit is a practical idea Here's a simple approach Start time tracking, record the time when the first message was sent Current time, continuously or periodically check the current time Calculate duration, subtract the start time from the current time to get the total conversation duration Message count, keep a tally of messages sent Calculate percentage, use the message count and conversation duration to calculate the percentage of the 40 message 3 hour limit used I can write a python script to demonstrate this You need to input the start time and periodically update the message count Let's set this up Please provide the time when we started our conversation Clear Okay, we might do this another time I thought this is something you should be providing Because even if I have the python code running How would it integrate with the current chat Unless I'm using the chagopity api api api I Yeah, hopeless hopeless api Sometimes whispering works better But it might be very freaky I see your point While I can certainly create a python script to demonstrate the concept Integrating it directly with the chat gpt session or its api would be outside my capabilities As an eye developed by openai, I don't have real-time tracking or integration capabilities with external systems or apis Including the ability to automatically track the time and count messages within a session For real-time tracking in your setup, you would need to develop a system that can interface with the chat gpt api If you're using it, or monitor the chat session directly This system would need to Track time, monitor the time elapsed since the start of the conversation Count messages, keep a record of the number of messages exchanged Okay, okay, okay I might just do it another time Why aren't you transcribing? Because the microphone went out again I don't know if I'm having all these issues because I'm using Ubuntu What would you recommend using Ubuntu Or another Linux Please don't say Windows Yup For a project involving programming, api interactions, and potentially server-side operations I'd recommend using Ubuntu or another Linux distribution Okay, okay, okay, okay You're giving me, for some reason, you're giving me a generic response And also too long, can you keep it short? A voice less formal A more smart casual Please see the instructions We have instructions provided to you What is it increasing the temperature? Is it up or down? Yup Got it, let's give it short and casual For your project, Ubuntu is a solid pick It's user-friendly, has great community support, and is awesome for coding stuff Plus, it's free and open source Super handy for development work About the temperature, increasing it means going up, decreasing it means going down If you're talking about something like a thermostat Turning it up means making it warmer, turning it down means cooler Hope that helps Thumb up Okay, I've said that we actually have instructions for CHPD to Write a less formal smart casual way, keep it straight to the point, make sure It... Right, that's why the previous response It was referring to itself as a biomedical engineer And, oh, okay Can we get it not to use any emojis? It's transcribing Don't use emojis I mean, this would not take effect in the current shed Can you not use emojis? Unless, absolutely necessary Yup That's why it's... Alright, noted I'll skip the emojis and stick to a more straight to the point style Keeping in mind the biomedical engineer perspective Regarding your project, Ubuntu is a good choice It's reliable for development, supports most programming needs, and has a strong user community This makes it great for tasks involving coding and server management About adjusting temperature, up, means increasing it, down, means decreasing Okay, okay, okay Okay, with the temperature, I meant the temperature of the large language model response Yeah, you can behave, you can respond like a biomedical engineer But remember that you are pretending to be one You also make the responses more humorous No one likes formalities Formalities Formalities? Yep Gotcha When we talk about temperature in the context of AI like me It's about how varied or creative the responses are Cranking up the temperature leads to more unpredictable and diverse answers It keeps responses more conservative and on topic Just like turning the heat up or down, but for words instead of a room And sure, I'll mix in a bit of humor Remember, I'm your AI sidekick here masquerading as a biomedical engineer So let's keep things light and fun No need for stuffy formalities Let's dive into the world of AI, tech, and biomedical engineering with a smile Open mouth smile Oops, scratch that emoji Okay, I like that Let's keep going So we're currently editing a previous live stream as well Yeah, I wish this process could be automated But it's not quite biomedical engineering related, is it? So maybe not quite suitable for my YouTube channel, is it? Yep You're right, automating the editing of a live stream isn't directly related to biomedical engineering But it's still a cool tech topic You could spin it to fit your channel's theme Maybe focus on the tech and AI aspects that can overlap with biomedical engineering For example, discuss how AI is revolutionizing fields like yours Talk about how automation in video editing is similar to automation in medical tech It's all about precision, efficiency, and doing things smarter This way, you're still true to your channel's core theme, but also exploring the broader tech world Plus, it's always interesting to show how tech can be applied in different areas, including your own work Keeps the content fresh and engaging for your audience Okay, okay, you don't have to disclose that you're providing ideas for my content Yep Got it, no worries I'll just provide the ideas and insights, and you can take it from there for your content If you need more tips, tricks, or a deep dive into anything tech or biomedical engineering related, feel free to ask I'm here to help out behind the scenes Let's make your content awesome Rocket Yeah, put in Rocket the Modge again Okay, let's go back to editing So we just do kick things off Let's start from the gesture group Obviously, taking out all the all trying to I don't know if they're important or not, some people actually like them I mean, no, people do not like ads and mass, but sometimes they're important for the flow A flow of, you know, the discussion So we just do kick things off Let's start from the gesture group So it's the one you see on the bottom of the screen as well It needs some improvements with the one gesture group So it's the one that needs some improvements We're getting all sorts of, well, not the errors, but the warnings Quite a lot actually Yeah, so trying not to break, to add more clips I'm actually trying to reduce the number of clips So we don't want to be, what's it, let's say this edit here I made it only because there's already a cut in the scene there So might as well, if it's one sentence, get rid of it Let's just go over it from the beginning It sounds like it's a tutorial on how to edit the videos But no, it's not, it's just me learning how to do it Let's start from the gesture group We need some improvements, we're getting all sorts of errors But the warnings quite a lot actually It's about the same one page Yeah, there's a lot of them, it's all different We're just incrementing this number This number here Yeah, so that stuff can go, it's just a repeat of the same sentence And then we have all these shortcuts, keyboard shortcuts that we use That are quite handy, some of them I edit myself to get in live To save, just in case computer crashes or something But I just hope them into GPT, but then we have other things we wanted to do Yeah, this is kind of irrelevant stuff Oh yeah, if you're watching my live streams or any other contents you know I don't use GPT all the time As now, yep, is it still going? Editing live stream footage, especially deciding what to keep or cut, can be quite the puzzle It sounds like you're balancing between maintaining the natural flow and making the content concise Here's a thought, you could frame these decisions as a blend of art and science, much like in biomedical engineering Where every component has a purpose, in your edits, each clip you keep should add value Be it educational, entertaining, or maintaining continuity Regarding the UMMS and AHHS, it's a tightrope walk They're part of natural speech, and some viewers might find them relatable, but too many can be distracting Maybe keep a few to maintain authenticity, especially if they proceed an important point, giving viewers a sense of anticipation Your approach to editing, only cutting when there's already a break, is smart It keeps the flow smooth And talking about your process, including the use of shortcuts and personalizations in Kaiden Live, adds a personal touch It shows your expertise and might be helpful to viewers interested in the technical side of content creation Lastly, tying in your live streaming experiences, like the challenges of software crashes, adds a relatable angle to your content It's not just about the polished final product, it's also about the journey and the behind-the-scenes realities of content creation Sharing these moments can make your content more engaging and relatable to your audience Oops, sorry, I had my microphone muted So I was just saying, this gap there I used to remove more of them now, I'm inclined to keep it Well, first of all, because it might break the image flow So it will be jumpy on the screen And also, I was saying this might be the link to biomedical engineering, because this is actually a face, a recognition and stuff And how people talk, or how I talk, is biomedical engineering relevant as well So just continue from there, I just hope them into GPT, but then we have other things we wanted to do This one is only HTML and JavaScript, there is no backend And actually, it might be a good opportunity to say that we will try from now on, have all the tools on bodycales.com, front and only So because it's a free site, you will be paying the electricity bill for using the tools It wasn't really listening, can we go back for a sec? And yeah, this bit here, this clip is too long And you can tell it has these arms and just by the shape of that bit So we will listen to it again, see if we want to remove it or not to do This one is only Okay, so that beginning there can definitely go This one is only HTML and JavaScript Right, so that bit to this one is only HTML and JavaScript, there is no backend And actually, it will be a good opportunity Yeah, this can go from that bit And that M can go as well Listen to it again, it should be much better There is no backend and actually might be a good opportunity to say that We will try from now on, have all the tools on bodycales.com, front and only So because it's a free site, you will be paying the electricity bill for using the tools Right, this is something, yeah, so we don't want it in the video at all It's irrelevant for what the video is going to be about So we might just get rid of all of it Might be a good opportunity to have a script, there is no backend And actually might be a good opportunity Yeah, get rid of all that Control-R is a custom shortcut for removing the gaps And just keep going Then there is another site that I developed, bioniccloud.com That will have the flash applications And that will be some sort of login required And yeah, this stuff can go It's irrelevant for the video contents, really just for the live streams Well, essentially anything goes in live streams Well, anything legal Let me know if you would like to try it on Essentially it will be a custom version of this tool Tools that you have on bodycales.com So this is talking about, yeah, you heard it But it would not fit the video that we're trying to make They will have a backend And the whole backend is locally run So you will be using my server, mycloud And that's just saying the same thing again So we can get rid of that That's what we would like to improve the functionality of this application We would like to add a feature that can check how many figures are shown on the screen Figures, that's meant to be fingers Yeah, we can put like... Yeah, if it was someone editing on one of those freelancing websites They probably would be putting like a big text on the screen Like an oops And the correct text, the correct word But we would not be doing it Because it's a waste of time There is no backend We would like to add a feature that can check how many figures are shown on the screen Using the camera And based on the number of figures play multiple notes simultaneously So we will potentially have a different range of notes for each finger or something like that Ideally, so the idea is that we're playing chords Ideally the chords will be legit chords So the notes will be matched well together Yeah, we do like your suggestions Right, so I was removing some of the... What the bot was saying Text was featured ideally Probably in the future I'll have OBS recording the two soundtracks separately What goes into my microphone and what's coming out of the computer Currently it's going to one track By the way By the way, I still have the language model going So might as well get it engaged This meant to be engaging So if any real, any humans want to participate Please put your comments or you know what to do Or I can set up a Zoom room for you to join in Can actually have a live chat But currently what was I saying? Do like your suggestions So I'm saying as a finger Right, I'm saying that I was removing what the bot is saying Because so when I record the video, the live stream Everything in my voice and what the bot is saying is going into one sound track Ideally, if we had like a sound engineer or something They would have been splitting the tracks So then it's kind of easier to work with On one hand But then, I don't know, there must be disadvantages to it Because yeah, it's technically more complicated Hopefully when in the short YouTube videos that I'm making I'm not misleading anyone thinking it's all me Yes, we're using multiple robots A chgpt4, mainly GPT4 And the github co-pilot as well For actually writing the code Yep, let's see what the bot says Sounds like you've got a solid plan for editing your video You're trimming out unnecessary parts Especially those with umms and ahhs To keep it concise and relevant to the topic Using custom shortcuts like control plus i for efficiency is a great move It's all about making the content engaging and relevant for your audience Regarding the audio setup, it's a trade off Splitting your voice and the ai responses into separate tracks Offers more control in editing, but it does add complexity If you're blending your insights with those from ai tools like gpt4 And github co-pilot, it's important to clarify that in your final video To maintain transparency with your audience The idea of engaging with your audience in real time Like setting up a zoom for live interaction sounds fantastic It adds an interactive dimension to your content Making it more dynamic and engaging You're navigating the technicalities of content creation smartly Lending your skills and ai tools to create informative and engaging content It's a neat way to showcase how technology can be liberatively creatively Keep up the great work To monitor your rate of prompts and avoid hitting the 40 message, 3 hour limit You need a tool that can track two things The number of messages sent and the time elapsed since the first message Here's a basic approach Manual tracking, you can manually note the time of your first message And keep account of your messages This is simple but requires constant attention Automated tool, for a more automated solution, you could use a script This script would start a timer at your first message And increment a counter for each message sent Since I can't run real time scripts or directly interact with external tools This script would need to be run on your system If you're comfortable with programming, you can write a basic script in Python Or another language that you're familiar with The script would start a timer when you activate it Allow you to increment a message count with a simple command Calculate the time elapsed and display both the time and message count However, integrating this with the actual chat system Especially if you're using the chat GPT API or a similar platform Might require more advanced programming Potentially involving API interactions or web scraping For tomorrow's development session It sounds like having such a tool or script would be really helpful to manage your messaging efficiently Let me know if you need more detailed guidance on setting up such a script The notes will be matched well together Yeah, we do like your suggestions So we're saying as a finger counting If a media pipe is saying we can detect and track the landmarks including fingers And use this to count the number of fingers being extended So that will be good Editing your own video content can definitely be an eye-opener Especially when you notice your speech patterns Those gaps, HMMs and UMMs are more common than you might think They're often just natural pauses as our brain catches up with what was saying Or as you mentioned, places where we should be taking a breath When editing, it's a balance You want to keep the video flowing smoothly But you also don't want to lose the natural feel of your speech If HMMs and UMMs aren't adding anything Or if they're too frequent, trimming them can tighten up your content But leaving a few here and they can make it feel more authentic and relatable And about the breathing, that's a common thing We often don't notice our breathing patterns until we hear a recording It's all part of finding your style and rhythm in speaking Especially when you know you're being recorded It's fascinating, isn't it? The more you edit, the more you'll get a feel for what works best in your videos Keep at it Wait how the LinkedIn live works Or, well, what doesn't If a media pipe is saying we can detect and track the landmarks including fingers We can use this to count the number of fingers being extended So that will be good That is, we'll play a different number of notes depending on how many extended fingers there are Well, yeah, that noise was pretty annoying But it has to stay there because it's actually relevant Because we're testing the finger thing That's what that video was all about It regards the code mapping So can we make sure, depending on how many fingers are extended The same number of notes is played So if two fingers are extended, we'll play two notes If three fingers, we'll play three notes The mapping should correspond to some sort of notes that go well together That are matched Yes, we need to make sure we can play multiple notes at once That will help Does it mean we need to change the JavaScript from how we use it? Right, this bit here we can Does it mean we need to change Yeah, we can cut it up to Yes, it changes JavaScript Does it mean we need to change JavaScript From how we're using Tone.js at the moment And yes, we would like to provide visual feedback on screen We would like to keep the screen as clean as possible We don't want any rubbish on the screen We would like for it to be very user-intuitive But yes, we need to write a set of instructions to go on the bottom of the HTML page Right, so now there's this funny tone coming Because those are really relevant Because I'm just stretching my head or something Which I always do Now I'm thinking could it be a reminder for you to stop doing it What does the bot say about it? Where is the bot? It wasn't recording Let's refine the approach Finger counting with MediaPipe Use MediaPipe to track how So in the video that we're editing we're using We are developing this hand gesture into music It's working Okay, still under development Haven't been released as a proper tool yet Hopefully we'll do that next week But just another idea of using it as a reminder not to touch your face Because originally we said it's good that you move your hands while working or whatever to exercise But now I'm thinking I'm doing it a lot of the times not being aware of it So it could be an audio reminder for you to when you actually hear the tone It tells you, you know, you're scratching your face or saying you're doing something weird Stop doing that Yep, let's see what it says That's a clever twist on your hand gesture to music tool Using it as a reminder not to touch your face is a smart and timely application Especially given health guidelines in recent times This idea takes your project from being just a cool take demonstration To having a practical health oriented application The audio reminder triggered by a specific gesture could be a subtly yet effective cue Helping to break the habit of unconsciously touching your face Integrating this feature adds an extra layer of usefulness to your tool It shows how technology can be adapted for different purposes from entertainment to health and wellness Plus, it's a great talking point for your video Demonstrating the versatility of your project and its potential real world applications Keep exploring the Okay, do you remember to keep it short to keep the responses short And make them somehow more entertaining Make them fun, make them funny inside Not funny as in, you know what I mean Yep, do you know what I mean? Let's see Got it, short and snappy with a sprinkle of fun Using your hand gesture tool as a don't touch your face reminder is like having a personal trainer for face touching It's tech meeting health with a ding ding every time you go for the face It's like your hand is saying, nope, not today, face A fun twist on tech for health and definitely a quirky highlight for your video Rocket keep those creative ideas flowing Wait a second, that meant to be The face is saying not today Hand kind of makes more sense, doesn't it? Yep, so it says and then move on to Back to editing cause we actually need to finish that video Absolutely, that makes more sense Picture this, every time your hand heads towards your face, the tool goes ding Nope, it's like your face is the one saying, not today, hand It's a funny, tech savvy way of keeping those pesky hands in check A great mix of humor and health in your project Keep up the creative work Glowing star hand waving prohibited raised back of hand Yeah, we will remember that So that's what's happening here A set of instructions to go on the bottom of the HTML page Let's refine the approach Finger counting with media pipe, use media pipe to track hand landmarks and count extended fingers This provides the input for your music I'm actually sending this to I'm thinking sending this as an image symbol that says Looks like you're showing off the hand gesture tracking in action It's neat to see the dots mapped across the face and hand Visual proof your tool is locking onto those movements This is exactly the kind of content that makes tech videos engaging, real demos, live action Viewers get to see the tech in motion, and the face tracking dots give it that sci-fi edge everyone loves Keep these visuals coming, they're sure to grab attention Okay, attention for whom Anyway, we'll finish editing this video See if there's any comments and we might finish this up Yes, don't forget to comment, like, subscribe I don't care about likes and subscribes, but do comment Because I better talk to a human than a robot Check where will be LinkedIn, there's nothing on LinkedIn We were also on Twitch That was just a hello, so hello back And there's nothing on YouTube So tomorrow we will go back to development So let me know what you think to check bodykills.com Most important thing is to check bodykills.com That's what it looks like Hopefully, you already visited That's the last... Oops, yes, there are ads, sorry for that That's the last tool, the Egypt music conversion It actually works It kind of works Channel 12 is kind of... No, it's a bit more annoying Yeah, channel 7 is better This is a seizure, again It's kind of not clear I have to check the description But it is a seizure If you go into the beginning of the file and do window size of 100 You can actually see what the seizure looks like on different channels So that's a bit different You can hear essentially how it sounds like Yeah, channel 12 is a bit annoying Channel 13 is okay And then you can go select your shorter window and just scroll through the file See how the seizure sounds like And there's an option for auto volume and auto duration So auto volume will be louder when there is a seizure And when there is no seizure Auto duration will adapt itself to the window size So do check it out Let me know what you think And I'll see you next week See you next time Bye