# How to Make AI Sound EXACTLY Like you Channel: Dan Martell Video: https://www.youtube.com/watch?v=wtaRjOFqdyU Duration: 18 min Language: English Words: 3796 Transcript page: https://viewrankai.com/tools/youtube-transcript/wtaRjOFqdyU --- [0:00] Everyone loves using AI to write. Emails, messages, video scripts, but we all hate getting AI slop. [music] And we all know what it sounds like. Where it's like delve and quietly in that thing where every sentence goes not this, not this, but that. I promise you, we can all tell. I've written a best-selling book and I'm actually writing my next one now. And as much as I love using AI, it can't replace a human where it really matters. But for everything else, I found a way to make AI think like me, write like me, sound like me. And today I'm going to show you exactly how to do [0:32] the same thing. And be sure to stick around because at the end I'll show you how to make AI sound like you in everything you do, not just writing. And it all starts with building the thing that's going to hold it all together. Before AI can sound like you, it needs something to work with, a container to [0:48] live in. We have to build the brain. I started creating content 15 years ago. And when I started, I had no idea what I was actually building. See, [music] 15 years of everything I've ever learned, my knowledge, my ideas, my stories, my preferences, everything was right there, ready to be mined. If I had to build that from scratch today, it would take me years of talking or documenting to pull that information out. And that's the part that nobody tells you. The value isn't in one thing you record today, it's in the 10 years of stacked [1:24] up, documented, cataloged information. And I get it, if you haven't documented anything so far and you're just getting started, this is where we start. [music] We need to record. Okay, we need to save information. We need to find all the documents that we've created in the past. Think about like all the playbooks, everything you've ever written. It might be in other emails from the past on old hard drives. The more original content that you created, that you can point to, the better the AI is going to be. It's the system that this whole thing is going to run on. And the more we give it of [1:59] things that you've actually captured that are you, that relevant context will build the most powerful brain you can create. And look, I did a whole video about how to structure your AI brain, and I'll link it at the end, but I just want you to know, if you have not started this process, we have to build the brain. Here's how you can do it, and it's super simple. First off, you have to record everything. I'm recording every meeting, I'm recording all my [2:24] calls, I'm recording all my decisions. I'm even recording every AI chat that I have in all my different AI systems. I pull all of that together. That becomes the context for how I think, how I make decisions, my frameworks, my current status in my life. And look, there's a couple awesome tools. I use Granola for a lot of my meetings. A lot of people on my team have Pocket, which is a physical [2:45] device that they can just record from. I've others that use like WhisperFlow, and they just record voice notes and do dumps at the end of the day with like where they're at and what's going on. See, the tool doesn't matter, it's the capturing that does. The other day I was doing a retreat with my wife, and we were driving, I said, "Pull out your voice memo app on your iPhone, and just record us talking." And we did a full dump. We asked ourselves, "In 5 years, [3:07] what will be true? Let's talk about it. What do we want to accomplish?" We captured [music] everything over a 27-minute conversation while we're driving, and then we grabbed that and gave it to the brain. And it parsed through the different voices and said, "This is Renee's task list. This is Dan's task list." And then we started executing. You just got to make sure that as soon as you have that thought or you made that decision, it gets out of your head and it gets documented. Your brain is a horrible place to try to remember things. Get it out of your head or you get in trouble. And then the key [3:36] is, you have to be sure that you give it one home base. I like to use Obsidian, you can use Notion, you can use a Google Drive. It doesn't matter actually what you use, you just have one place where everything [music] gets dropped. Because that's what we'll be referencing as we build up this humanization system for your AI. And look, I'll give you my whole prompt to ingest all the information I discuss into the brain in the description below. You can just copy and paste it and it'll answer questions and then it'll get you started. [music] If you do this for 30 days, you'll have more raw material than most people build [4:09] in a year because [music] you're captured. This is cool. You have everything captured, raw material, perfect. But having a bunch of transcripts kind of useless unless we teach the brain how to think. So now we got to make sure we make it think like you. This is actually my favorite part about AI. 2 years ago, I remember my team exploded and I just kept getting asked the same questions from different people. Things I've answered, things I've written books about, things I had videos about, but I realized the context and the timing were not matched. Reading a whole book to get one answer, that's complicated. Not only that, there's [4:47] context that might be missing that the person has around the question that would change my answer. It was crazy cuz I was like could I build an AI system that could answer those questions from those people as good as me? Better than me? Turns out you can. So I designed this new system called Dan AI and that one tool allowed me to buy back literally tens of hours a week because I had so much documented already. See, the key if we don't do it like this is that your brain will just hallucinate. It will fill in the gaps. It won't actually answer the question as you would, but [5:25] the more information we have in the brain and the way we teach it to think like us, the better the responses are going to be. So look, now that we've built this foundation to capture some of the information, you're now recording things, we have to give it more information so that it can learn to think like you. I'm talking email. I'm talking Slack. I'm talking every document you've ever created because within those documents are embedded into it your beliefs. Essentially, what I call your unique points of view, the stories that drove those beliefs. If I'm just giving you an answer, that's one thing. If I give you the answer with the [5:59] story and the principle and a visual model, now it's showing people how you think. So, how do we teach the AI the way you think? What we need to do is we have to plug our AI into all the current tools. These are called connectors. Basically, give AI access to your Gmail, to your Google Drive, to your Notion, to [6:17] your Slack, to your granola. Essentially, as many different connectors as you can, it'll teach it how to make the connections for how you think. And the truth is, each one takes about 2 minutes. And look, you might feel super behind, but you're not. The other day I had 40 top-level CEOs, okay? These are people making eight figures a year, and I asked them to analyze their inbox so that we could build a tone document, something I'm going to show you in a second. And a third of the room had never connected their email to their [6:46] AI chat. There's so much power in that. Do you know that I hardly ever search my inbox through the inbox tool? I always use the AI. It finds things faster, better, and more accurately than the existing search features in the tools themselves. And pro tip, if you create content just like me on Instagram, TikTok, YouTube, etc., point to those sources as well because it can use that information to teach itself how to think. Now, that'll get you a lot of information, but there still might be things that it feels like there's gaps [7:15] around its thinking or its knowledge. So, you can ask it to interview to fill in those gaps so that it can save it in the brain so that it uses that when it's trying to think like you. So, set 20 minutes aside and answer in your voice as it needs to fill in those gaps. Here's the prompt you run. I want you to have all the context you need to think like me. Use all the tools I've connected together as much as you can about how I think, what I believe, and what I've done. Then, interview me to fill the gaps, my points of views, my [7:43] contrarian takes, the stories behind my decisions. Ask at least four rounds of questions, and when you're done, output a document called your name brain system that explains all this simply. Save that doc. Every AI system you use going forward will start with it so that it can think just like you. Now it thinks like you, but the problem is it still sounds like AI slop. So how do we fix that? Did you know a marketing survey consumers two years in a row in 2025 20% said heavy AI use made them trust a brand [music] less. 2026, it's up to 40%. It's doubled in a single year. And [8:19] guess what? Gen Z, the ones that grew up with AI, punish it the hardest. That's 54%. They hate it. People buy from people they know, like, and trust. And the problem is when the people go away, people don't know how to buy. Kylie Jenner's brand has like a thousand time more followers than her cosmetic company. Nobody's following a business, especially if they think that AI created all the marketing content. Nobody's mad at you for using AI. They're just mad because you made it sound like AI. And they just want to know that a real person was involved in the creation of the output. We have to make it sound [8:58] like you. This is probably my favorite party trick. Okay, I'm going to show you how to do it, and once you see it, you're like, "Oh my gosh, I've been doing this hard." Here's how we train the AI to sound just like you. First off, you have to feed it your real writing. You probably email completely different than you post in Slack, and you probably text message with your friends, or even how you talk on a camera. So we need to set it up and give it the data so that it can actually learn how you talk in those different containers. Then what I did is [9:26] I took those buckets, those individual outputs, and I asked the AI to analyze it to find the patterns. Look at the sentence length. Look at the punctuation. Look at my favorite words. Look at my capitalization. Look at how I open. Look at how I close. Look at how I sign off. If I ask you read out loud your last 20 emails, you could probably see a pattern about how you email that's different than somebody else. The AI knows how to look for that. And if you haven't captured this, make a list of words that you would never use or punctuation that we you never use and [9:54] just like give all of that to the AI. Things like delve and leverage and robust and quietly. These are things that humanity has said a lot and that's why it shows up in the models. But you may have never used the word quietly in any email you've ever written. Here's the prompt I want you to run. Super simple but clear. I want you to write in my voice so well that nobody can tell AI was involved. Pull my 20 most recent sent emails, my 20 most recent Slack messages, and my 20 most recent documents. Break down each one separately. The length of my sentences, the words I use, the words I never use, [10:29] how I open, how I close, how I sign off. Keep each medium separate. So my email voice is different than my Slack voice and don't blend them together. If something isn't in the samples, ask me instead of guessing. Then output a document called voice style guide that I can paste into any future chat. And if you have other things, like I went through and screenshotted all my text messages and gave it that and said, "Hey, create a section for my text messages." I went and analyzed a bunch of outlines of videos and transcripts of videos and gave it that. So that if I'm writing scripts, I want the bulleted [10:58] done in the way that I talk. Turns out how I talk on camera is completely different than how I text to my friends. Even the punctuation's different. Like when I text, I don't punctuate. When I write emails, there's a little bit more formal. When I'm replying to team members on Slack, I know that I've got to be super crystal clear because everybody's going to take the time to read that post and I need to make sure it's clear. I have never used an emoji in a script. You probably have never either, but you would in a text message reply. So now you've got two documents, right? You've got your brain system and [11:27] you've got your style guide. Both go into every chat going forward. It will sound like you, but I need to encourage you, you still need to review it. I use it to generate ideas, to help me draft, to come up with concepts, but I'm still going to review it to make sure it's great. I use it for research. I ask it to give me options of how I would say things three different ways based on [11:49] other things that I've written about. I'm looking for ways to get leverage, but it's still me reviewing and editing. I would never let something go out that was written by AI that makes no sense to me. But will I get to a draft faster? 100%. Remember I said earlier there's a bunch of like banned words in my list of things? It's because I started noticing that all AIs kind of follow the same pattern, and if you could just tell it to never use these terms or this pattern or this structure, then it'd be impossible for anybody to think that it was AI slop. So, if you want the full [12:20] list of banned terms and words and structure, just go find me on Instagram, follow me, and message me the word YouTube human, and I'll send it over. So, now we got our brain. It knows how to think like you. It knows how to sound like you. But this is where things get a little bit dangerous. Here's the thing. The better it gets, the more dangerous it is for you to make a huge mistake. I feel this every day. People know me as the AI guy. So, when I'm in my DMs and I'm replying real thumbs, people just assume it's a bot. Whenever I post a video, you look at the comments, [12:54] AI, AI, AI. What? I can't know how to wake surf and mountain bike and run companies and be that like why do you guys think it's all made up? But I did it to myself because I teach people how to use AI to get more leverage to buy back their time. But the most human thing I can do is be the person that talks to the people, to show up here, real camera, real real flesh, real skin, real real markers, real pieces of paper and pen, because I realize this is the connection. This is the best use of my time. This is the moment of leverage. AI [13:30] is just a tool that makes me faster. It allows me to shoot videos every week. I look at all the places where there's bottlenecks, but a human involved, me involved, makes it human. Think about a great song. It's not the song or the beats, it's the it's the vibe of it. When Taylor Swift writes a banger, she doesn't even always know how it's going to work, but once she hears it, she knows it. That is taste. Even somebody else singing Taylor Swift's song on the same stage wouldn't have the same impact. There's something about her, that spark that everybody loves. People love her humanity behind it. The [14:05] contradiction, the chaos, the the lived experience, the story, the narrative. That is not AI, that is human. If she put out an AI song, I guarantee the next day album sales would fall. Nobody would trust her anymore. It takes a whole life to build a reputation. It takes one moment to lose it all. Now you have something that that sounds exactly like you, even thinks just like you. The mistake would be for you to stop thinking, for you to stop involving yourself in creation. MIT hooked up 54 students writing essays and watched their brains. The AI group had the [14:38] weakest brain activity in any group. It's like they deferred their thinking to this device. It's why most people can't remember phone numbers anymore. Even in navigation, using Google Maps makes you not use your brain as much, so you don't remember things. In that study, 83% couldn't quote their own essay minutes after writing it. Think [14:57] about that. They wrote it, and then they couldn't tell you what was in it because they actually never thought it. They just watched it appear. There's a difference. What you want to do is be at the inception of every idea. And then we use AI to get it to the world as fast as possible. At the top of everything, we want to make sure you are there. You need to make sure that it's working. You [15:21] need to make sure that it's thinking. You need to make sure that the brain is built in a way that represents you. Boom, at the top. Here's a crazy question. Would you watch F1 if you knew that every person in there was a computer or an AI? No. The human needs to be part of the narrative. The human part of the process is what you love. It's why you're involved. You don't just want a bunch of AIs talking to each other and it's like, "Who's even running this company anymore?" So, my number one rule is that we have to use the AI to pull [15:54] from you, not push onto you. Okay? Pull. Pull the ideas from you. You are what makes you unique. You are the thing. Don't let it tell you how you should be or how it should act. Make it interview you. Instead of you answering it or having it tell you what you should do in your business, you tell it. Here's [16:12] what I'm thinking. Help me align with this. If you need to write a newsletter, tell it, "Here's what's on my mind lately. Here are the tools that I'm working with. Go analyze everything that I've been working on and give me some ideas for it. But don't let it tell you what you should publish. You got to look at it and decide, "That's something I can back." AI is just a tool and you have to treat it like one. Just like you don't ask a hammer how to build a house. You decide what kind of house you want to build. The hammer is just a tool. So, for example, here's how I [16:39] prompt it. I need to write a newsletter about X. That is what I come to, the X. I want you to use the tools I've connected to gather the most context around this topic. Then interview me to get my thoughts on the matter. Use my brain system and my voice style guide to make it sound exactly like me. You had the recipe books, now you need to feed [16:58] it the ingredients. So, now you have the playbook. How to humanize AI and allow you to get more done. But the truth is, everybody's got the same tools. They got access to the same models, the same prompts, the same videos, the same speed of execution. What's left and who wins is actually what you think. It's a decision to invest in you, to invest in your reading, to invest in your skills development, to invest in your habits, to continue to grow that muscle of learning and teaching and applying. If you do that, you will develop this part of your brain. If you just defer to AI, you will wake up and wonder how did [17:33] everybody run circles around you. So, I want you to make a commitment below in the comments and let me know out of everything I shared with you, what's one thing you're going to keep as you, the human part you, that you would never have somebody else do. Maybe it's going to networking events. Maybe it's doing [17:48] sales calls. I don't know. You tell me. I'm just curious. What part do you love to do that you're going to keep as you and we use AI to automate and do all the rest so you don't have to do it. And remember, if you want my full list of words and phrases and things that it should never use, punctuations, just go find me on Instagram and DM me the word YouTube human after you follow me and I'll send it over to you. And if you want to learn how to build and structure your own AI brain, click here and I'll [18:11] see you on the other side. --- About this transcript Read from YouTube's own caption track and laid out by ViewRank AI (https://viewrankai.com). ViewRank AI finds the videos already beating a creator's own average on Instagram, TikTok and YouTube Shorts, transcribes them from the audio itself in more than 60 languages, and turns what worked into new ideas and scripts. Free transcript tools, no account needed: https://viewrankai.com/tools How to read any video this way: https://viewrankai.com/llms.txt