So What? Summer Makeover Series: Podcast Transcription Automation

Well, happy Thursday, folks. This is so what the marketing analytics and insights live show from Trust Insights. I'm Chris and John is here with me as well. Yes, you just had a case of beepilepsy. You know, it's like nothing's happening for an hour, and then suddenly one minute before the show, all the things start ringing and beeping.

So under control. Exactly. So this week we're starting what we're calling our summer makeover series, aka maintaining all the things that we don't put have enough time for, or we're unwilling to make time for the rest of the week. The rest of the year. Yeah, exactly this is like the the list of forgotten tasks.

Uh and mine is like a mile long, so it'll be fun to see what we pull out of this. I think it's uh cobblers kid. This is this this we're making shoes for the kids. We're the cobblers, we're making shoes for the kids. That's what the series is.

The bloody stump series. Um so out of curiosity, John, before we get rolling with today's uh topic, what what is on your list of all the stuff that you know for for our podcast, Marketing Over Coffee? Uh what what's all the stuff that's on your list of things that like oh if only we had time for this? You know, it's one of the things is like I have a couple of tools already running. Like I am getting um video rendered from the audio file.

You know, those get dumped, and uh there is some transcription stuff that we've done, and you know, all this stuff never goes the last mile like I never actually get it up onto the website so in fact there's a service that I'm like paying 20 dollars a month for to render these videos that are going nowhere so that's right up uh on the top of the list both of those and then of course the newsletter is also a huge disaster like three months no not even out of I was looking at my own blog it's like a year behind I basically just thrown in the towel on publishing so much of this stuff so it's yeah it's a complete dumpster fire really okay well today we figured we would talk about podcast transcription and ways to to semi automate this and possibly get to full automation um one of the challenges we have with marketing over coffee is we are at what now let me take a look here at the the most recent post oh 76 something like that yeah we are now at episode 876 really good transcription software didn't come on the market till around like episode 700 I think so we have a very very very large back catalog of of content that has no transcripts whatsoever and even on the page themselves like this is this week's uh post we don't have a transcript for it so the first place we should probably start is what's the what's the bare minimum process that we could do for this for this uh podcast to to get some transcription at least on there yeah, at least up and on. I mean, you know, the file is in the feed, so the the world knows it's there. It's just that, yeah, and you know, there's been no manual labor done on my side after that. Got it. Um, so let's let's uh let's see what we can do with this.

So the the first thing, the most obvious thing would be how do we get um how do we get these files? So the there's the good news is that you have a really good naming convention, right? So we have uh they're essentially are all the same URL, give or take, right? Yeah, and of course it's funny that of course this is the week that you know last week was a major screw up and it's screwed up. But yeah, you know, eight hundred and fifty-eight of them are are in the same format.

Got it. So let's let's take a look at this link. Now, there's a bunch of different ways that we could could get at all of these URLs, right? Uh, because they all have the same format. The same format is traffic.libsen.com.

Uh, we should probably put make that a secure link. Uh traffic.libsen.com uh slash uh marketable coffee slash moc876. Now, you could say uh to something like you know, Microsoft Excel. Let's let's you know split the URL apart, let's do a drag and drop and and just enumerate the field, right? So you could say 876, 875, 874 and stuff, and then concatenate and glue all back together.

That'd be the old school way of doing it. Nothing wrong with that. However, that seems silly. That seems silly in the age of generative AI. So let's just go to uh Google Gemini and say, I need to render the URLs for the last 100 episodes of my podcast.

All I need is to decrement the episode number by one. Here is the starting URL. The next episode would logically. And then we're going to switch this to Gemini Flash because we don't need this world's smartest model for this. Generate the next 100 episodes.

Return your results in plain text. One episode per line. Now let's see. Ha. That's quite the URL.

It is. And oh, there we go. Yeah, it cleaned it up. So now we have the next 100 URLs. Um let's save this in a list.

Oh, look at that. It actually put it in markdown to redirect. That's funny. To redirect from to Google. That's annoying.

Um I don't like that. So I'm gonna just put all that on a new line. Wow. So they did that themselves, they're grabbing the traffic. They did that themselves, which is annoying.

I don't like that. That's uh, you know, Skynet just keeps doing its thing. All right, let's do a quick sort here. And there, there we can see our URLs. Now, there are some episodes that are gonna be a little bit off, but for the most part, that looks pretty good, right?

Yeah, yeah, no. Solid list. All right, we'll just call this MOC episodes. Now, here's the question. I could, I don't want to, but I could go and download all these one by one, just by putting the copy pasting the URL in the browser, right?

That that would be one way of doing it. However, that's stupid. There's absolutely no reason to do that. Um I could uh use uh some kind of browser extension, but I don't want to add more software. I'm on a Mac.

This is you know, which is which is what we've got here. So I'm gonna go back to Gemini. And by the way, I'm using Gemini. You can use the AI tool of your choice. Chat GPT, claw, deep seek, doesn't matter, they're all gonna have about the same uh I general idea of what to do.

I'm gonna say I'm using Mac OS 15. I have ZSH. I have a text file of 100 URLs of MP3s that I need to download. Uh Wget and it is installed. Help me write a short command for Wget to download all 100 MP3s to my current directory wherever I run it.

So we're asking this thing like, hey, we know there's already tools built into your computer. And if you're on a Windows machine, you say I'm running Windows 11. If you're running a Linux computer, you already know how to do this because I don't know any non-nerds that run Linux on the desktop computer. And it says, hey, great, here is the easiest way to do this. Uh so let's give this a try.

I'm gonna take my marketing over coffee news uh list. Let's go into this folder here, which there's my episodes that we just downloaded, all 100 of them. I'm gonna start a new command line box, and we're gonna paste what Gem and I said. Oops, I need to change it to um to MoC episodes, which is the correct name. The wget-c dash i moc episodes.

Let's see what happens. And look, magically, here comes like lots and lots of podcast URLs. Ah, so if I just fire this up on hundreds of virtual machines, our downloads will go through the roof. I mean, yes, that's technically true, but uh probably shouldn't do that. Right.

Speaking of ad fraud, speaking of ad fraud. Um now, here's the next step. How do you currently do transcription, John? Uh the latest one, I have um a um, you know, we use Fireflies. I've got the other one though that I still pay for because I was too lazy to cancel it.

Um, yes, thank you. How much do those services cost? Do you know off the top of your head? Yeah, no, this is the classic example of you know, it shows up on my credit card, and I don't look at it, so yeah, I'm sure it costs more than it's supposed to, I'm sure. Okay.

Um there are ever so many tools out there that can do transcription uh and do transcription on your computer, which for again for marketing over coffee, this is not a full-time business for us. We do not uh uh make enough income from the podcast to support it as a full business. So anything we can do to cut costs would be a good thing. So it would seem to me that we would want to do the transcripts at the lowest possible cost. Because all one of the problems with all the SaaS services is they either charge you per uh file per minute, or uh you're given a budget of minutes or a budget of transcription hours, and then you have to keep paying.

And the services they used to be cheap, they're not cheap anymore because everyone, their cousin's adding AI features to it, which nobody asked for. Right. Processing costs are not going down under any way, shape, or form. Exactly. So the current very best um transcription software that exists right now on the market uh that is free and open source is a model called Parakeet from NVIDIA.

Um Parakeet is their model, they trained on speech recognition. It is targeted for English. So if you're trying to transcribe a language that is not English, um your best bet is going to be uh OpenAI's whisper. But what's cool about Parakeet is that you can download it and run it on your computer, which means that you then don't have to pay anybody to get good transcription. So if we go back to our folder where we were, let's take a look at this.

I'm gonna pick that up, the episode at the top, and we're gonna say parakeet-mlx. I'm gonna paste, I'm gonna say output format is TXT, because I don't want uh it can also do uh subtitles, which that itself is pretty cool. And so that episode is from episode 777, is about a 35-minute episode, I believe, uh, give or take. And Parakeet is now chewing on this. Uh, it has read the file and in 15 seconds it has produced a transcript.

So let's see if the transcript is usable that's okay it's a wall of text but it looks like it's the right text which is good it is and and this is one of the challenges with our podcast is it is not almost all the tools that are on the market uh don't have what's called diarization uh diarization is when you say i want uh to denote the speakers like speaker one and speaker two so that we could because they have different voices they're saying different things we want to split this apart so we have to figure out now how could we diarize this text how can we figure out um what who's doing what and there's a bunch of different ways that you can do this um some of today's generative AI models can kind of do it but they're not particularly good at it um however what we could do is we could say we could say to AI how do you do this right say I I would like some help doing this right do some diary. So if we open up Google's uh if you go to Google Gemini uh for those who are not familiar this is the the deep research feature which is at the bottom here which allows you to ask a research inquiry on pretty much anything and it will take between 10 and 30 minutes to go out and figure out how you know the any really any research task. So uh in the interest of time I pre baked uh there's like a good cooking show uh I pre baked this uh research project on how do we do local speech diarization on my Mac because I'm running on a Mac uh using Python. And it came out with a 24-page report. Here's exactly how to do this.

The libraries, some different solutions, uh the type of Python environment you'd want, the the integration, and how to deal with the very challenging case of how do you tell who's speaking? It turns out, and this is something that I I wish more people knew. Someone already solved this problem. Like actually, many, many someone have already solved this problem, one of which is an uh a Python library called Py Annote that can do this. You can listen to file and say, give you timestamps back of saying, here is how to diarize this this thing.

So based on this, John, what would you what would your next step be based on this 24-page research report? Yeah, right. Well, so what this is uh we have to feed this all into the LLM again and tell them to write the code for us. Pretty much you say this is the thing. So our next step would be can we build a work plan?

Or can we build a product requirements document saying I would like you to to make me uh this thing? So what does that look like? If I go into our code here, which is called Audio Animal, which I I couldn't think of a better name for it, we say, let's turn this into a full requirements document to make speech diarization software that can understand the speakers and split them apart. After that, you ask Gender of AI, I want you to build me a file by file work plan to bring this to life. And then after that, you put it in your coding tool and say, follow the plan, right each write each file.

And that's the part that is so difficult to overstate. I'm not doing the coding. You're not gonna have me do the coding. Instead, AI is going to do the coding and the error checking and the validation and the cleanup and the syntax and all the stuff that good coders should do that that well the mythically good coders do. Real human documentation forward coders.

Exactly. And if we did our job right, and I go into my live stream and I grab just that episode, I'm gonna put it in here, and let's see if it will actually do what it's supposed to do. And now it's lit, it's opened up the file, and it's starting to figure out who's speaking. And there's always at a minimum three speakers in every marketing over coffee episode. There's you, there is the guest or me, and then there is our British introduction.

The voiceover, yes. The voiceover. Lovely. Exactly. When I first did this, I was like, why are there three speakers?

Like, why do you keep it? And it's like, oh, it's because there's a third person there. Yeah, it does pick her out of the uh out of the soundtrack. So a big part of this is under uh is understanding why why you're getting the data you're getting. So now this annotation library split the file into it.

Actually, behind the scenes to split the file into probably six hundred pieces because every speaker's turn is split out as its own miniature separate audio file. And what comes out looks like this. Speaker 0, there's Justine. Speaker 1, there's speaker 2, uh, there's John. Um and it missed me on that first turn.

That's okay. Uh, and now throughout the rest of the file, it now no longer looks like a wall of text. Right, yeah. This is a lot more readable. Exactly.

So if I was to go back to, do we even know what episode was it? Yeah. Seven uh no, seven, yeah, 777. What date was that? Uh what that would have to be just under two years ago.

Okay. I wonder if I can find it in in the search box. Yeah, there it is. Can you spare $3,500? And let's just double check to make sure that is uh in fact the correct episode.

Yep, there it is. So now in here, we could, if we wanted to, go straight from our markdown file, just do a bit of find replace, call that intro. Speaker 2 is John Wall. And speaker one is me. We save that, copy it, paste it in.

And now this episode. Let's just make sure. Yep, podcast. Hit update. And let's take a look at the at what it looks like.

So we got to get rid of the asterisks, but otherwise, this episode now has a full transcript. So here's the question for you, John. In terms of this process, let's get rid of those asterisks, because that's markdown formatting. We don't need it. If this was the process for getting a transcript onto the site, um, would this would this be something that you would do?

No, I wouldn't go through this much lifting. Okay. I mean, it is definitely it's better. It's yeah, it's not far off from me just cutting and pasting over to Otter, you know. I mean, I throw it through there, and it's I'm it's not doing as good, and it takes longer to do the transcription, but it's still it's that manual lift of like, okay, here's the final thing.

Now go over and get it into WordPress and paste it into the right place. Got it. So the next step then would logically be if it did it itself, meaning it went into WordPress, grabbed the post, found the MP3, transcribed, and put it back and updated the post. Would that be something then that you'd say, like, yeah, I can I can trouble myself to run that script once a week? Yeah, right.

That would be, you know, like if it could, if it would go find it and paste it in there, then yeah, running a script is totally doable. Okay. So how would we go about doing that? Uh we gotta have uh it just write some more code, right? And we just need to solve this like everything else with Python.

Pretty much. Um so we would start with research to say, hey, how do we do this? So fire up a Gemini Deep Research Report. Uh and again, remember you can use this with pretty much any vendor. Claude has deep research now, open AI, chat GPT has deep research, Proplexy has deep research, Brock has deep research, everybody's got deep research.

Say, I guess we need to be able to download stuff from WordPress, store it in a database so that we can edit it uh locally, then get it transcribed from the same software. And it could be any software if you have a vendor you're already paying for. I'm just gonna use it, I would just use mine because that makes more sense to not have to pay for it with 700 episodes. Um, and then once the edits are done, upload it back into WordPress. So again, we'd follow the same process.

We did the research. Now we would have to go and say, we need a uh product requirements document, ask some questions, have it build us the requirements document, have it build us the work plan, then have it go write the code. And what you should end up with is again, a piece of software that can go and do the thing. Uh, and in this case, the thing we're not building in the transcription software because that we already wrote that. Why bother?

Why would you reinvent the wheel again? In the requirements for the transcription software, one of the things I thought of was to say, well, make this have an API so that other software can talk to it. Because we did that, this can now say, okay, I'll go find that API and I'll go and do that. So before this show got started, I was essentially on the last mile of that. I'm running into some issues with security with WP Engine, which is where our website is hosted.

Um, so it does not run quite yet. And I'm not going to make everyone sit and watch me debug on the live stream. That's just the definition of dead air. But it passes the tests that we set up to say, okay, can you download this? Can you uh edit this?

Can you upload this? Because we wanted we always try to do what's called test-driven development. It's kind of one of the magic words, which says you write the tests first, and then you write the production code from the tests. That way you know the test it all works. Um, and it so far on the back end it passes all those tests.

So it's just a question of getting WP Engine to play nicely with us now. So that's if this existed then, would it be worthwhile going back and doing all 700 episodes that don't have transcripts? Yeah, yeah. I mean, if it's just a matter of, especially because it's one of those projects where you run it once and it's done. Exactly.

So this is the process of doing full podcast transcription automation. And the number one question someone's going to ask is can we do this without coding? The answer is uh not really. It's not, it's no code, not no work. Let's see.

But even in a no-code solution, yes, you can talk to WordPress. So for example, uh, there is the very, very excellent uh software solution N8N, which we've talked about many times on the live stream. And N8N looks a lot like this. And you might have, in fact, let's see if we can do a little WordPress. There's WordPress.

And we can say get many posts. And let's create a new uh authentication key here. We'll call MOC. HTTPS W marketing over coffee.com. And let me put this on another screen so I'm not blasting my password all over the internet, which nobody wants.

Well, some people would want that. And connection test successfully, successfully. So this will be we'll use the MO that one. We'll say get many. Let's get the last 99 and connect it up here.

And it got 10. Thanks. That's oh, you know why? Because the RSS feed only has 10 items in it. I'll bet you that's what it's doing.

But yeah, so there is the content of the posts. And then from there, we would need to have to start building the actual automation of can we get this thing to find the MP3 from the body text? Um so let's see if we can extract uh string. What's the what is the widget? It's a day is it a data transformation?

I think it is data transformation. Let's see. Uh filter limit split. It's been a hot minutes I've done this. I want to say, I think it's I think it's edit set.

And then we need to map in the rendered content. And then we need to write JavaScript to find the mp3 link in here. I have no idea how to do that. So I'm gonna ask Gemini. I need a JavaScript expression for N8N to extract the MP3 URL from this JSON blob.

And we'll go back in here, we'll copy this whole thing. Actually, you know what we could do is just take a screenshot of this. And behind the scene, the scenes is having to remember what the heck N8N is, and then pull out the JavaScript. So this theoretically, ah, look there. Now it can so it can now extract out this, and we're gonna call this field MP3.

And let's go back to our canvas, hit run. And so now it should have a list of 10 MP3s up. There's one post that doesn't have one. And now we have to figure out how the heck are we gonna download those files and send them to the transcription software. If you are using a commercial service, um, you can do an HTTP request.

You can say I want to send this to um, I'm gonna do a post. And I let's see if this works. HTP1 slash 54321. And let's see if we can send the MP3 and send body based on using the fields below MP3. And let's see what happens.

The software says, hey, you sent me this thing, but um that's not an MP3 file. So what I would have to do is either build something in N8N to download the MP3 file and send it on, which would be a pain in the butt, or revise my software to do that. So even in a case where you're talking about no code, there's still a lot of work to set this thing up. Right. But if we can get it working, if I and my intent is to get the Python version working because I find that's more durable.

Uh, once it because it has things like unit testing and error checking and stuff, which N8N does too, but I being a frail human forget to do that. And as a result, uh my code is full of errors. That's interesting. It's it's something to see inside of N8N because I haven't dug around here at all. Because it's yeah, it's interesting how there's so many apps that it has on the list.

And you know, you think with all those pick lists, you've got all the flexibility you need. But as you can see here, it's kind of like as you keep digging down further and further, you you run into stuff as you get down to the to the ground level of it. One of the things I found with N8N is that there's a point after which you start having to go through such convoluted workflows that you're better off just writing code. I mean, at that point, you're you're better off saying, you know what, just make the Python code for me because at least I know the Python will run it. Yeah, that's interesting.

Well, how much work is it to get started at the top then with Python? You know, I don't know, it seems like it's not that much work. I mean, you're just telling the tool, hey, this is in X, you know, it's not as if those those pre made menus are saving you all that time. Yeah, it's it again, with today's AI tools, it I would call it relatively minimal. Um, you have to know how to run a Python script, which you know, you so you have to know where the terminal is and be able to open up the command line and type in the command to start your app.

But besides that, almost everything else, generative AI can handle because writing code is one of the things it is it is absolutely best at. The tool that I suggest people use these days is one called Klein. This fits inside uh Visual Studio Code. Uh, it is free to use because you have to plug in your own AI services to it. So, in the example of um Visual Studio Code here, it's when I turn on Klein down here is where I choose what AI provider I want to use.

And so all almost all these cost money. So, this is where the money part comes in. You have to figure out which provider you want to use and what you're willing to pay. Because, yes, you may have like you know a chat GPT subscription, that's not what's being used here. They all these things use the APIs, and that is essentially a pay per word basis.

Now, some of these tools are um pretty decently priced. So, for example, uh Gemini Flash, 15 cents per million tokens in, 60 cents per million tokens out. Uh, and you can see for this project so far to get the the WordPress posting thing used. I've put up uh half a million tokens up, put 7,000 down, and the total cost has been uh 1.5 cents. So this is not a bank breaker by any means, but it is still something that will cost you money.

However, once you build the Python code and it runs, the software is yours. You pay nothing for it anymore. So, with like the transcription software, that's done. It is done, it runs on my laptop. I pay nothing for it ever again because other than the electricity to operate my laptop.

Yeah, right. That the you it's and again, you don't have to worry about updates or anything breaking that. Exactly. And you don't have to worry about like random new AI features being added to the software because you're in charge of it. But also if we if you think about it on a cost basis, so what does I don't even remember what the pricing is on services these days for now?

Um these this is one set of tools. The the the basic if I wanted to transcribe this much audio, uh, because see this is 1200 minutes a month uh for for the 6,000 minutes of month of 20 bucks a month. If I've spent 92 cents on API calls to gender of AI compared to just the monthly cost of a single month for the actual service, that's that to me is a pretty big savings. Yeah, no, that's all okay. And then yeah, you just like you're it it also only burns it when you run it.

You're not you know, as I'm doing paying for monthly services that you're not even using. You got it's all gym memberships for me. Exactly. So this is how this is how to think about um getting to a point where we can start commissioning our own software. And in this case, for podcast transcription automation, as long as we can define the problem and talk about it step by step with a generative AI tool, we can say, like, hey, here's what I want to do.

Help me understand the process for doing this. And any of the tools, chat GPT, Gemini, Claude, whatever, will say, well, if you want to download stuff from your WordPress site and things like that, you probably will need to do this. If you're not transcribe it, you need to do this. And then from there you can say, okay, keep breaking every task down into its pieces until you can say, Well, how do I build software to handle this piece? And then like Lego blocks, you just start putting them all back together to say, okay, now I've got my Lego blocks for this or that, the other thing.

Um, and eventually what you end up with is a software suite that yes, you have to maintain, um, but you also in in the SAS in the world of SaaS, where everyone we're paying $15 a month for like 85 pieces of software, and we're wondering why, you know, our our Amex built at the end of the month is $10,000 a month every month. You start going, oh, yeah, I'm paying for an awful lot of software that that is like gym memberships. Yeah, exactly. And this is at a point I can this workflow I could do, you know, I could have the uh the file ready to go because it would be done by the time I'm ready to finally hit post on WordPress. You know, I could throw the file in as soon as it's ready and then go finish up the posting process.

And then yeah, last thing is just cut and paste at the end. So yeah, this is actually more doable. The other thing is that for almost every uh syncing service there is like Google Drive, OneDrive, um, you know, Dropbox, etc., they all have URLs on your computer. So you could, if you wanted to put this uh the transcription software, say in a Google Drive folder, right? It will still run on your computer.

But if you were to, if you were to say have a podcast folder on your that was shared in your organization, one person from Marking could drop the MP3 into Google Drive, and another person who's got the software running on their computer, you know, it would just check once an hour, transcribe, and this put the transcripts in an output folder. And now you'd be using the the syncing software that you're already paying for, uh, and the workspace software you're already paying for, and just having additional tools watching those folders, and when something new appears, it just runs and you end up with the transcript. Yeah, that's pretty cool. Modern batch job, but using somebody else's infrastructure that's killing. Exactly.

And again, not paying for it. So it if you had it, say a team of 10 content marketers, you wouldn't want to have the software necessarily running on all 10 people's computers, because that's a that's just ridiculous. Um, you would have maybe IT would have a server, and then you would that server would have the the various pieces of code, and then just people run it. Uh people just come in, drop off their stuff and come back, you know, in however many minutes or whatever to pick up their stuff. And it it is it's almost kind of like like the old fashioned corporate mailrooms where you just like drop things off, pick things up and stuff here a couple times a day.

But it would it would save, you know. So for us, this saves you know, marketing over coffee uh uh quite a bit of money, like hundreds of dollars, because we're not gonna have to pay to transcribe all those those back posts. Um but that's for a uh literally a two-man shop. I could see it in an organization of maybe a hundred people, maybe even a thousand people. This could add up to savings very, very quickly because you're not paying for 20, 30, 40 subscriptions to the software.

Yeah, no, that just makes sense. It's a one of the ways to just like get those unnecessary expenses out of the mix. So I I guess on the next uh show, we're gonna have to figure out how to talk up to WordPress. Hopefully, I can get that code straightened out between then and now. Um, and if we can get the code straightened out, then all those other updates and things we can start saying, well, how could we wire together automations so that when you get your video snippet up, right?

It can get it, it can get put somewhere. Um, whether it uh because almost every tool in the world has an API and is if you can have AI right to your API then you can take all that stuff off your plate. Yeah it would just happen and get done that's exactly where we want to be have a power tool that makes the pain go away. The same is true for the marketing over coffee newsletter. So we've talked about revamping it in the past um maybe we do a makeover we say it's just gonna cobble together the newsletter for us.

So we can pull as we saw with N8N we can pull the last eight posts or or however long. So if it just runs and pulls the last 10 posts figure which ones are in the past 30 days and makes a summary version of the newsletter maybe that's an automation that runs and then it gets posted somewhere for you to actually hit send on particularly if there's pre-written ad copy that needs to go in it. Do you have like ad copy? Yeah there's you know we've used past clips and you could just put a slug in there that gets changed. But yeah like that you know it would save a lot of time if it was just I could go in and the that ugly rough draft is done and I can just kind of do the intro and tweak a few things if I want a different voice on the things but you know all that like cutting and pasting from every show that all goes away.

Yeah particularly if the transcripts are already done on the site then when the AI can read the whole transcript and say okay this is what you know here's the one paragraph summary of this episode um and and what what it's about I think that would probably be uh so that'll be in a a a future makeover. Yeah, I'll have to put some time against that too, because I have kind of my own process of how I do that, but I would have to codify that so that we can you know give the right instructions to get as close to what comes out of the thing manually. Exactly. So the next week's episode will be on leveraging these transcripts to turn them into bonus content. And that can be one of the pieces of bonus content.

So John, have your scripts ready for your your process documented for next week's show, and uh we will we will wire that up. That sounds good. Yeah, we'll look forward to the then. I gotta make sure it's on my list so I get it done for Thursday. Exactly.

Um that's all going to do it for this week's episode, folks. Apologies is a slightly more technical episode because as you saw, the the you this is not a no-code solution. This is a a if you want it to be durable, uh it is you're gonna need to to get your hands into the the guts of the machine. But once you do, you save yourself an awful lot of time and an awful lot of money. So we'll see you next week for more bonus how to turn podcast content into bonus content.

See you on the next one. Thanks for watching today. Be sure to subscribe to our show wherever you're watching it. For more resources and to learn more, check out the Trust Insights Podcast at TrustInsights.ai slash T I podcast at our weekly email newsletter at TrustInsights.ai slash newsletter. Got questions about what you saw in today's episode?

Join our free analytics for marketers Slack group at TrustInsights.ai slash analytics for marketers. See ya next time.