WEBVTT 00:00:00.240 --> 00:00:03.279 I've been teasing for a while that I made some major podcasting 00:00:03.279 --> 00:00:06.639 workflow changes on The Audacity to Podcast and asked you to 00:00:06.639 --> 00:00:09.519 guess. Now here's what I did. 00:00:16.015 --> 00:00:18.894 Thank you for joining me for The Audacity to Podcast. 00:00:18.894 --> 00:00:19.935 I'm Daniel J. Lewis. 00:00:19.935 --> 00:00:23.255 I've been podcasting since 20 o 7, and I started The Audacity to 00:00:23.255 --> 00:00:24.894 Podcast in 2010. 00:00:25.054 --> 00:00:29.535 And I started the episodes doing them in a particular way, and 00:00:28.980 --> 00:00:31.619 somewhere along the way, and I don't know exactly when this 00:00:31.619 --> 00:00:36.820 changed, but I changed how I prepared for the episodes as well as 00:00:36.820 --> 00:00:40.579 how that affected how I recorded the episodes, and that affected 00:00:40.579 --> 00:00:42.179 how I then produced the episodes. 00:00:42.575 --> 00:00:46.734 And more recently, I've made a major change back to an original 00:00:46.734 --> 00:00:47.854 way I was doing it. 00:00:48.015 --> 00:00:51.454 I've also made some other workflow changes that I wanted to share 00:00:51.454 --> 00:00:54.574 with you because these could inspire your own podcasting workflow 00:00:54.574 --> 00:00:55.854 changes and improvements. 00:00:56.289 --> 00:01:00.450 And I have been teasing this for a little while asking you to 00:01:00.450 --> 00:01:02.289 guess what it was. 00:01:02.370 --> 00:01:06.930 And a few of my listeners did guess correctly what kind of 00:01:06.930 --> 00:01:09.810 changes I've made since late 20 25. 00:01:10.225 --> 00:01:13.025 And even though I'm recording this in 2026, I wanted to give 00:01:13.025 --> 00:01:16.944 enough time to really see how I liked these changes, how they 00:01:16.944 --> 00:01:21.505 were working for me, and if anyone noticed, especially if anyone 00:01:21.505 --> 00:01:24.465 complained if they could tell what the changes were. 00:01:24.850 --> 00:01:28.609 So let's start with number 1, chapters and transcripts. 00:01:28.770 --> 00:01:31.329 But not just chapters and transcripts in general because I was 00:01:31.329 --> 00:01:32.370 doing that before. 00:01:32.530 --> 00:01:36.290 More specifically, chapters and transcripts with PodChapters. 00:01:36.530 --> 00:01:39.495 Before PodChapters, which is my own product, please try it out on 00:01:39.495 --> 00:01:41.975 your next episode over at podchapters.com. 00:01:41.975 --> 00:01:46.295 Before PodChapters, I was spending 30 to 60 minutes across about 00:01:46.295 --> 00:01:51.255 5 different tools, even on 2 different computers in order to do 00:01:51.255 --> 00:01:55.950 what PodChapters now does for me in about 30 to 60 seconds. 00:01:56.270 --> 00:01:59.230 It creates a transcript for me, or I could bring my own 00:01:59.230 --> 00:02:03.150 transcript if I really wanted to as long as it's VTT or SRT, but 00:02:03.150 --> 00:02:06.350 it generates the transcript for me, which does a lot better and 00:02:06.350 --> 00:02:10.705 faster of a job than my other computer does, which my main 00:02:10.705 --> 00:02:12.625 computer can't do transcripts very well. 00:02:12.625 --> 00:02:14.465 It's very slow at transcripts. 00:02:14.465 --> 00:02:17.344 So I'd have to go over to my other computer to have it do the 00:02:17.344 --> 00:02:20.145 transcript for me and then bring that back to my main computer. 00:02:20.145 --> 00:02:22.629 It was cumbersome. And so many apps to use. 00:02:22.629 --> 00:02:24.389 I know 5 isn't a big number. 00:02:24.389 --> 00:02:28.389 But for such a simple thing, going between 5 different apps, 30 00:02:28.389 --> 00:02:32.469 to 60 minutes, and some of the apps were clunky, slow, just 00:02:32.469 --> 00:02:35.110 didn't work very well, had massive frustrations for me. 00:02:35.294 --> 00:02:39.055 So I started building PodChapters because I wanted to improve my 00:02:39.055 --> 00:02:40.735 own podcasting workflow. 00:02:40.814 --> 00:02:43.935 When I first started creating it, I wasn't planning to turn it 00:02:43.935 --> 00:02:44.974 into a product. 00:02:45.294 --> 00:02:49.694 But once I started making it work, I realized, wait a minute. 00:02:50.080 --> 00:02:53.040 Other podcasters can actually benefit from this too. 00:02:53.199 --> 00:02:56.479 And the podcasters who have signed up for PodChapters are loving 00:02:56.479 --> 00:02:56.879 it. 00:02:56.879 --> 00:03:00.159 And they're using it episode after episode, and it's saving them 00:03:00.159 --> 00:03:02.879 so much time too. And it saves me so much time. 00:03:02.879 --> 00:03:08.115 What used to take me 30 to 60 minutes now takes 30 to 60 seconds, 00:03:08.435 --> 00:03:13.235 and that's not an exaggeration. It is so fast for me to use. 00:03:13.395 --> 00:03:16.995 I'm loving it even just for myself, and other podcasters are 00:03:16.995 --> 00:03:17.634 loving it too. 00:03:17.634 --> 00:03:20.799 So I'd love for you to try PodChapters on your next episode. 00:03:20.799 --> 00:03:23.680 There's a free trial, so that gives you enough time to try it on 00:03:23.680 --> 00:03:24.639 your next episode. 00:03:24.719 --> 00:03:27.759 You can bring your own transcript to save on the AI credits, or 00:03:27.759 --> 00:03:30.639 you can have PodChapters transcribe your episode for you in the 00:03:30.639 --> 00:03:33.875 proper format, and then it can generate the chapters for you. 00:03:33.875 --> 00:03:36.915 And then that transcript that it provides, you can download that 00:03:36.915 --> 00:03:40.275 or you can use the transcripts or the chapters hosted by 00:03:40.275 --> 00:03:41.235 PodChapters. 00:03:41.395 --> 00:03:46.329 And that's going to provide an ability to do some cool stuff in 00:03:46.329 --> 00:03:48.889 the future. Some little tricks I have up my sleeve. 00:03:48.889 --> 00:03:52.009 And 1 of the tricks I have up my sleeve that's been a significant 00:03:52.009 --> 00:03:55.609 productivity and workflow boost to me with PodChapters is that 00:03:55.609 --> 00:03:58.969 I've wanted something for years and have asked other developers 00:03:58.969 --> 00:04:01.465 and apps to try and build in this feature. 00:04:01.465 --> 00:04:03.465 No one's done it, so I finally did it myself. 00:04:03.465 --> 00:04:06.825 And that is that when I record my episodes, I know my outline, 00:04:06.825 --> 00:04:08.985 and I want my outline to be my chapters. 00:04:09.145 --> 00:04:12.425 So I know what I want my chapters to be. 00:04:12.425 --> 00:04:16.370 I just don't know where they should be in my audio. 00:04:16.610 --> 00:04:21.810 So I wanted a tool that would allow me to paste my own outline 00:04:21.810 --> 00:04:26.290 without time stamps, and it would find where that outline exists 00:04:26.290 --> 00:04:30.564 in my episode and then turn that outline into chapters. 00:04:30.564 --> 00:04:34.404 PodChapters now does that, and it does it so fast, so well. 00:04:34.404 --> 00:04:38.404 I just go in sometimes and tweak by half a second or so just to 00:04:38.404 --> 00:04:39.925 be more precise on things. 00:04:39.925 --> 00:04:43.290 But from dropping my episode into PodChapters to downloading the 00:04:43.290 --> 00:04:46.730 episode back again, and it's fully chaptered and transcribed and 00:04:46.730 --> 00:04:51.930 ID 3 tagged and all of that is about 30 to 60 seconds of work. 00:04:51.930 --> 00:04:52.730 I love it. 00:04:52.834 --> 00:04:55.795 This has been a huge boost for me and for other podcasters too. 00:04:55.795 --> 00:04:59.074 So I'd love for you to try it try it free, in fact, over at 00:04:59.074 --> 00:05:03.475 podchapters.com. And number 2 is the bigger change. 00:05:03.475 --> 00:05:06.435 The thing that I've been hinting at for months because I wanted 00:05:06.435 --> 00:05:10.419 to see if anyone noticed what was different, and they could 00:05:10.419 --> 00:05:13.459 actually guess exactly what I had changed. 00:05:13.620 --> 00:05:17.540 And that is I went back to outlines instead of scripts. 00:05:17.540 --> 00:05:21.680 I don't know exactly when I did this along the way of The 00:05:21.680 --> 00:05:25.305 Audacity to Podcast, but I basically started scripting my 00:05:25.305 --> 00:05:26.105 episodes. 00:05:26.264 --> 00:05:30.264 I would write my show notes ahead of time as an article, and that 00:05:30.264 --> 00:05:32.985 would help me to formulate my thoughts, figure out my 00:05:32.985 --> 00:05:35.785 transitions, get all my links together, all of that stuff. 00:05:35.785 --> 00:05:38.345 So it really helped with the preparation of the content. 00:05:38.800 --> 00:05:44.080 And that way, when I press stop on my recording, I already had my 00:05:44.080 --> 00:05:47.360 show notes done, and they were in article format. 00:05:47.520 --> 00:05:50.960 And I felt like I presented the content very well because I 00:05:50.960 --> 00:05:53.520 essentially rehearsed it by writing it down. 00:05:53.954 --> 00:05:58.514 And since I speak the way I write generally, and generally write 00:05:58.514 --> 00:06:02.274 the way I speak, they were very close to each other. 00:06:02.354 --> 00:06:07.920 But that's also where a little bit of laziness and perfectionism 00:06:07.920 --> 00:06:11.920 at the same time somehow snuck their way in. 00:06:12.000 --> 00:06:16.240 And it started getting cumbersome to write the script ahead of 00:06:16.240 --> 00:06:16.800 time. 00:06:16.879 --> 00:06:19.759 And there were a lot of ideas that I had that I just didn't want 00:06:19.759 --> 00:06:20.560 to write the script. 00:06:20.560 --> 00:06:24.024 Or even just in recording the script, I would be talking along. 00:06:24.024 --> 00:06:26.985 I would stumble over a way I say something, and because I had it 00:06:26.985 --> 00:06:31.625 written down, I wanted to say it that particular way, so I'd have 00:06:31.625 --> 00:06:34.345 to go back and say it again. 00:06:34.345 --> 00:06:39.360 And that actually created more edit points than if I just spoke 00:06:39.360 --> 00:06:40.720 off of the outlines. 00:06:40.800 --> 00:06:44.720 And part of the reason that I kept doing this, even after being 00:06:44.720 --> 00:06:48.399 on a very long hiatus from The Audacity to Podcast, is because, 00:06:48.824 --> 00:06:54.425 getting personal here, my confidence took a really big kick from 00:06:54.425 --> 00:06:57.704 multiple bad things that have happened in my life that I don't 00:06:57.704 --> 00:06:58.985 need to go into here. 00:06:58.985 --> 00:07:03.220 But it really made me doubt my ability to communicate. 00:07:03.220 --> 00:07:07.860 I even remember when my unwanted and unfortunate divorce started. 00:07:08.019 --> 00:07:11.300 That first podcast movement, I was basically a walking zombie 00:07:11.300 --> 00:07:12.339 walking around. 00:07:12.660 --> 00:07:15.939 I still kind of wanted to go and especially because I wanted to 00:07:15.939 --> 00:07:18.964 shine the light on my friend, Dave Jackson, because I got to 00:07:18.964 --> 00:07:21.925 introduce him as he was being inducted into the Podcast Hall of 00:07:21.925 --> 00:07:22.165 Fame. 00:07:22.165 --> 00:07:25.685 So I was really excited to do that and support my friend that 00:07:25.685 --> 00:07:29.205 way. And the rest of the time, I was like a zombie. 00:07:29.205 --> 00:07:31.205 I couldn't talk very well. 00:07:31.205 --> 00:07:36.699 I stumbled over basic concepts, and I was, like, broken. 00:07:37.100 --> 00:07:40.060 And that carried over for a while. 00:07:40.060 --> 00:07:44.379 And even when the emotions rebuilt, still the confidence was gone 00:07:44.379 --> 00:07:47.845 and the ability to communicate as smoothly. 00:07:47.925 --> 00:07:51.764 And I'm not saying this to say I'm like some master communicator 00:07:51.764 --> 00:07:55.925 or anything like that, but the confidence was gone. 00:07:56.084 --> 00:08:00.979 The feeling of I know what I want to say and how I want to say it 00:08:00.979 --> 00:08:01.860 was gone. 00:08:02.019 --> 00:08:06.979 And so I started relying on the script to help me as I was 00:08:06.979 --> 00:08:08.819 getting back into podcasting. 00:08:08.819 --> 00:08:12.259 And it was then easy that I could have the script in front of me, 00:08:12.339 --> 00:08:16.014 look into a teleprompter, and read that script pretty much 00:08:16.014 --> 00:08:16.895 verbatim. 00:08:16.895 --> 00:08:20.814 I would occasionally go off script, but since I write generally 00:08:20.814 --> 00:08:24.654 the way I speak, and generally speak the way I write, it didn't 00:08:24.654 --> 00:08:29.535 sound too much like it was scripted, but it did still sound 00:08:29.535 --> 00:08:30.335 somewhat like it. 00:08:30.759 --> 00:08:37.160 And so I wish I actually wrote down what episode I changed. 00:08:37.399 --> 00:08:42.840 I think it was around episode 410 of The Audacity to Podcast 00:08:42.840 --> 00:08:47.725 where I decided I'm gonna go back to outlines instead of a 00:08:47.725 --> 00:08:48.285 script. 00:08:48.524 --> 00:08:52.684 Because for 1 thing, I was starting to feel more confident, and I 00:08:52.684 --> 00:08:56.845 was starting to feel like the script was confining me somewhat. 00:08:56.924 --> 00:09:01.019 And I felt like I had the energy again to kind of ad lib, but not 00:09:01.019 --> 00:09:01.899 completely ad lib. 00:09:01.899 --> 00:09:06.379 It's still prepared, but to be more off the cuff, more dynamic, 00:09:06.379 --> 00:09:10.139 more engaging at a human level, like I'm having a conversation 00:09:10.139 --> 00:09:10.539 with you. 00:09:10.884 --> 00:09:13.845 And I felt like the script was starting to limit that, and I 00:09:13.845 --> 00:09:16.964 wanted to get back into that because that's how I was when I 00:09:16.964 --> 00:09:18.565 started The Audacity to Podcast. 00:09:18.565 --> 00:09:20.964 Not how I was when I started the the ramen noodle, my first 00:09:20.964 --> 00:09:21.444 podcast. 00:09:21.444 --> 00:09:25.700 That was totally scripted, And the first 9 episodes in 2 years 00:09:25.940 --> 00:09:30.019 took so long to do because I was scripting them to perfection. 00:09:30.019 --> 00:09:35.220 But that aside, switching back to outlines, I could feel the 00:09:35.220 --> 00:09:36.339 energy was different. 00:09:36.575 --> 00:09:39.455 And that's what I heard from several of my listeners. 00:09:39.534 --> 00:09:43.934 A couple of them did guess that I was maybe not using a script 00:09:43.934 --> 00:09:44.735 anymore. 00:09:44.815 --> 00:09:49.695 But what all of them who guessed said is your energy sounds 00:09:49.695 --> 00:09:53.940 different. You sound more passionate, more energetic. 00:09:53.940 --> 00:09:57.860 Like, there's more of something of you behind the episodes. 00:09:57.860 --> 00:09:59.779 And that's true because it is me. 00:09:59.860 --> 00:10:02.965 Now I am still using a teleprompter, like I promoted 00:10:02.965 --> 00:10:05.924 teleprompters in my episode about teleprompters a few episodes 00:10:05.924 --> 00:10:06.565 ago. 00:10:06.644 --> 00:10:10.085 But now all that's on the teleprompter in front of me is my 00:10:10.085 --> 00:10:10.804 outline. 00:10:11.044 --> 00:10:14.485 Maybe a couple of reminders here and there of some certain things 00:10:14.485 --> 00:10:19.259 I want to remember, like an episode number or URL or a particular 00:10:19.259 --> 00:10:22.539 point I want to make or maybe a quotation I do want to read. 00:10:22.620 --> 00:10:25.419 But I'm looking at just my outline as I'm actually looking 00:10:25.419 --> 00:10:28.379 directly into the camera and I see my outline. 00:10:28.539 --> 00:10:33.125 And I like being back to outlines instead of scripts because it 00:10:33.125 --> 00:10:36.804 reminds me so much of the passion for public speaking, which was 00:10:36.804 --> 00:10:40.725 something else I missed during those several years of a hiatus. 00:10:40.804 --> 00:10:42.485 I enjoy public speaking. 00:10:42.485 --> 00:10:45.125 I've enjoyed it since I was a teenager when I started public 00:10:45.125 --> 00:10:47.445 speaking even though I was super nervous back then. 00:10:47.669 --> 00:10:51.350 I still get nervous when I publicly speak, but it's something I 00:10:51.350 --> 00:10:52.629 really enjoy. 00:10:52.629 --> 00:10:56.470 And this feels like I'm back into that passion again, and I have 00:10:56.470 --> 00:10:57.350 more energy. 00:10:57.429 --> 00:11:01.190 And what's really been interesting to me to discover is my 00:11:01.190 --> 00:11:05.804 editor, John Buchanis, has said that he doesn't have to edit me 00:11:05.804 --> 00:11:10.925 as much when I'm now talking from an outline instead of from a 00:11:10.925 --> 00:11:11.485 script. 00:11:11.644 --> 00:11:16.605 And I know for 1 reason, that's because I don't have the verbatim 00:11:16.605 --> 00:11:20.509 thing in front of me, so I don't have to worry about reading it 00:11:20.509 --> 00:11:25.310 perfectly or getting my timing just right for how the sentences 00:11:25.310 --> 00:11:26.430 connect together. 00:11:26.670 --> 00:11:29.950 Also, I'm speaking kind of off the cuff or ad libbing or working 00:11:29.950 --> 00:11:33.475 from an outline, really, If I start going the wrong direction in 00:11:33.475 --> 00:11:37.554 a sentence, instead of having to stop, figure out what I wanted 00:11:37.554 --> 00:11:40.514 to say, and start over again with a different sentence, sometimes 00:11:40.514 --> 00:11:43.634 I just roll with it and go with a different direction of a 00:11:43.634 --> 00:11:46.299 sentence like that. So I really like this. 00:11:46.299 --> 00:11:50.300 And if you've been doing your podcast episodes from scripts, 00:11:50.700 --> 00:11:54.779 maybe you've been doing it long enough that maybe you're ready to 00:11:54.779 --> 00:11:58.299 cut that umbilical cord, and you could start podcasting, 00:11:58.715 --> 00:12:01.595 recording your episodes without a script. 00:12:01.674 --> 00:12:03.754 That doesn't mean you don't have notes. 00:12:03.754 --> 00:12:07.355 That doesn't mean you don't plan what you want to talk about. 00:12:07.514 --> 00:12:09.674 But give it a try if you haven't yet. 00:12:09.835 --> 00:12:14.169 Maybe it will boost your confidence to try it and see, wow. 00:12:14.169 --> 00:12:16.889 This actually is fun. I feel totally different. 00:12:16.889 --> 00:12:20.169 And I feel totally different as well when I'm talking from a 00:12:20.169 --> 00:12:23.690 script instead of from the outline. 00:12:23.929 --> 00:12:26.169 And right there, I'll give a little side note. 00:12:26.235 --> 00:12:29.914 Right there is where I just did 1 of those things where I meant 00:12:29.914 --> 00:12:33.754 to say, I feel a lot different talking from an outline, but I 00:12:33.754 --> 00:12:36.794 used the word script first. So I just ran with it. 00:12:36.794 --> 00:12:40.154 And I then switched how I was going to say that, and I said the 00:12:40.154 --> 00:12:44.960 script, and I fixed it by then continuing on with the sentence. 00:12:44.960 --> 00:12:48.399 And that kind of thing is how we communicate in real life. 00:12:48.639 --> 00:12:53.040 And I feel like, even though I don't see you, I feel like I'm 00:12:53.040 --> 00:12:57.565 communicating at a more personable level with you. Do you agree? 00:12:57.725 --> 00:13:01.004 Do you feel like the episodes sound or feel different? 00:13:01.004 --> 00:13:04.845 Do you feel maybe more connected to me based simply on the way 00:13:04.845 --> 00:13:07.644 I've been communicating differently in the last several episodes? 00:13:07.725 --> 00:13:08.684 I'd love to hear from you. 00:13:08.684 --> 00:13:12.950 Send me feedback at podcast feedback dot com slash audacity or 00:13:12.950 --> 00:13:16.309 reach out on pretty much any social network as the Daniel J. 00:13:16.309 --> 00:13:16.870 Lewis. 00:13:17.029 --> 00:13:20.870 1 of the other reasons that I made this change is for my personal 00:13:20.870 --> 00:13:24.950 schedule wise because I have John Buchanan editing my episodes 00:13:24.705 --> 00:13:25.184 for me. 00:13:25.184 --> 00:13:28.304 That has been 1 of the best investments for me in podcasting is 00:13:28.304 --> 00:13:31.745 having someone else do that because I do not enjoy editing my own 00:13:31.745 --> 00:13:32.545 episodes. 00:13:32.625 --> 00:13:35.985 That's why my first podcast only had 9 episodes in the first 2 00:13:35.985 --> 00:13:37.345 years of its existence. 00:13:38.139 --> 00:13:41.899 When I have to write the script before I can press record, that 00:13:41.899 --> 00:13:45.580 means it takes me longer to press record, which means then it 00:13:45.580 --> 00:13:48.940 takes me longer to get that episode to John to edit. 00:13:49.019 --> 00:13:53.355 So if I can get the episode to him quicker, he can edit it at a 00:13:53.355 --> 00:13:54.554 more convenient time. 00:13:54.554 --> 00:13:57.274 And I'm still working on my personal schedule to try and give 00:13:57.274 --> 00:14:00.794 more margin for things and do things at a consistent time each 00:14:00.794 --> 00:14:01.434 week. 00:14:01.595 --> 00:14:04.875 But now that I can talk from an outline instead of having to 00:14:04.875 --> 00:14:08.580 write the whole script ahead of time, it means I can jump into 00:14:08.580 --> 00:14:10.019 the episode quicker. 00:14:10.180 --> 00:14:13.779 But then what about the article that goes along with it or as 00:14:13.779 --> 00:14:18.340 many of us would call it, the show notes? Well, that's number 3. 00:14:18.500 --> 00:14:21.554 My episode articles, and I've always tried to take the approach 00:14:21.554 --> 00:14:24.914 of writing them like an article or maybe kind of like a blog post 00:14:24.914 --> 00:14:28.595 because there are a lot of personal pronouns in there, the me, 00:14:28.595 --> 00:14:30.674 the my, I, and stuff like that. 00:14:30.834 --> 00:14:33.315 I've started using AI for this a lot more. 00:14:33.315 --> 00:14:34.730 Now, please hear me out. 00:14:34.730 --> 00:14:40.730 I am still not a fan of using AI to create the content for you. 00:14:40.809 --> 00:14:44.889 You create your own content, but you can use AI on your 00:14:44.889 --> 00:14:50.304 creativity to repurpose, to reformat, to restructure, to do 00:14:50.304 --> 00:14:53.664 things with that. Pod chapters, that's what it does. 00:14:53.664 --> 00:14:59.345 It takes your transcript of you and your cohost speaking, and it 00:14:59.345 --> 00:15:04.090 does cool stuff with that, turning your spoken content through 00:15:04.090 --> 00:15:07.850 your transcript into chapters. That's AI doing that. 00:15:07.929 --> 00:15:10.570 So it's not making AI slop. 00:15:10.730 --> 00:15:15.610 It's making stuff from your original thought and creativity. 00:15:15.769 --> 00:15:19.210 And that's what I think AI should be used for, not to create 00:15:19.210 --> 00:15:24.304 things for us, which are really artificial things then, but to do 00:15:24.304 --> 00:15:29.424 stuff with our own creativity, what we put our own brain cells 00:15:29.424 --> 00:15:30.384 into making. 00:15:30.544 --> 00:15:36.610 So I've started using AI to turn my transcript and my outline 00:15:36.769 --> 00:15:41.169 into the articles and blog posts, but not just simply giving it 00:15:41.169 --> 00:15:44.129 my transcript and saying, turn this into an article. 00:15:44.209 --> 00:15:48.545 I do more beyond that, and part of this has been built with 00:15:48.545 --> 00:15:52.545 OpenClaw and continues to be managed by OpenClaw or maybe at some 00:15:52.545 --> 00:15:54.384 point I might switch to Hermes agent. 00:15:54.384 --> 00:15:58.545 And by the way, I'm still looking for your ideas of how you use 00:15:58.545 --> 00:16:03.399 any kind of agent like that, Open Claw, Hermes, Paperclip, 00:16:03.399 --> 00:16:06.440 anything like that where you can run software locally to do 00:16:06.440 --> 00:16:09.320 things on your computer using an AI agent. 00:16:09.399 --> 00:16:12.679 I'm going to do an episode about different ways you can use that 00:16:12.679 --> 00:16:14.200 in podcasting in the future. 00:16:14.200 --> 00:16:17.125 So if you want that episode to come out, send me your ideas or 00:16:17.125 --> 00:16:20.004 even just your thoughts, suggestions, questions that I can cover 00:16:20.004 --> 00:16:24.245 in that episode. Go to podcastfeedback.com/audacity for that. 00:16:24.404 --> 00:16:27.125 So because of what I've been doing it with Open Claw, I've 00:16:27.125 --> 00:16:30.420 discovered new ways that I could make this better. 00:16:30.500 --> 00:16:34.580 And the first thing was that I took the transcripts from all of 00:16:34.580 --> 00:16:35.860 my latest episodes. 00:16:36.019 --> 00:16:39.379 In fact, all of the episodes that have transcripts with them, 00:16:39.460 --> 00:16:43.299 which at this point is, I think, maybe more than 50 episodes, 00:16:43.644 --> 00:16:47.084 which all of those transcripts combined together would make a 00:16:47.084 --> 00:16:52.284 document which would be way too big to feed into any AI engine 00:16:52.284 --> 00:16:54.684 out there, an LLM, a large language model. 00:16:54.684 --> 00:16:59.340 It's not that large of a language model to hold that much content 00:16:59.340 --> 00:16:59.980 in it. 00:16:59.980 --> 00:17:02.940 So if you hear people talking about, yeah, just put all of your 00:17:02.940 --> 00:17:06.140 transcripts into an AI and have it do something with that. 00:17:06.140 --> 00:17:09.259 Well, it's going to miss some of that content because these 00:17:09.259 --> 00:17:11.500 things have certain input limits. 00:17:11.845 --> 00:17:15.365 Instead, what I had it do, and using OpenCLUD to do this, is I 00:17:15.365 --> 00:17:20.005 had it systematically go through every episode's transcript and 00:17:20.005 --> 00:17:22.325 analyze how I talk. 00:17:22.485 --> 00:17:25.605 Recognizing that, yes, many of those older transcripts are me 00:17:25.605 --> 00:17:29.440 basically reading a script, but still the script was written the 00:17:29.440 --> 00:17:32.799 way I write, which is very close to the way I talk. 00:17:33.039 --> 00:17:37.519 So it went through episode after episode, 1 at a time, analyzing 00:17:37.519 --> 00:17:41.644 how I talk, certain figures of speech I tend to use, certain 00:17:41.644 --> 00:17:45.724 phrases I repeat over and over, my patterns, certain things like 00:17:45.724 --> 00:17:49.804 that, just the way that I communicate as well, my tone, my 00:17:50.044 --> 00:17:55.269 language, my intelligence level to say for how I communicate. 00:17:55.269 --> 00:17:58.789 Am I communicating at a collegiate level or at a third grade 00:17:58.789 --> 00:17:59.990 level or anything like that? 00:17:59.990 --> 00:18:03.590 So it analyzes all of that episode after episode, and it starts 00:18:03.590 --> 00:18:08.630 building out a voice document or a tone of voice document that 00:18:08.630 --> 00:18:11.244 describes how I communicate. 00:18:11.484 --> 00:18:14.765 And I have currently open Claude, but maybe in the future Hermes 00:18:14.765 --> 00:18:15.965 agent or maybe something else. 00:18:15.965 --> 00:18:17.805 We'll see because I might switch things around. 00:18:17.805 --> 00:18:20.204 But I have it every time I publish an episode. 00:18:20.205 --> 00:18:24.349 It goes, looks at the transcript, and updates that tone of voice 00:18:24.349 --> 00:18:27.789 document with any new patterns that it recognizes. 00:18:28.029 --> 00:18:32.430 And by now, most of the time, it doesn't see anything that's all 00:18:32.430 --> 00:18:33.309 that different. 00:18:33.309 --> 00:18:37.015 It's adding just an occasional note here or there to recognize a 00:18:37.015 --> 00:18:41.335 certain phrase that I repeat sometimes or maybe a new pattern 00:18:41.335 --> 00:18:43.095 that it hasn't detected before. 00:18:43.095 --> 00:18:45.015 But it's not making a whole lot more. 00:18:45.015 --> 00:18:48.299 But the point is now I've got this tone of voice document that I 00:18:48.299 --> 00:18:52.700 take that document, I combine it with my transcript and with my 00:18:52.700 --> 00:18:57.499 outline, and I ask the AI then to use all of this stuff together 00:18:57.659 --> 00:19:03.424 to turn my transcript into an article, put in my voice, in my 00:19:03.424 --> 00:19:08.704 tone of voice, from my first person perspective, and the results 00:19:08.865 --> 00:19:10.065 are really good. 00:19:10.065 --> 00:19:14.384 They're very, very close to what I would have written myself. 00:19:14.799 --> 00:19:19.200 I don't know these days how effective the systems are that try to 00:19:19.200 --> 00:19:22.240 detect what is AI or what is not. 00:19:22.400 --> 00:19:25.519 If you dare look at my content and say, oh, you have an em dash. 00:19:25.519 --> 00:19:28.160 You're using AI because there's an em dash. Hey. 00:19:28.424 --> 00:19:30.984 I've been using em dashes since the nineties. 00:19:31.144 --> 00:19:34.505 I still remember the code back when I was on a Windows computer. 00:19:34.585 --> 00:19:39.225 Hold down alt, and on the number pad, type the number 0 1 5 1. 00:19:39.225 --> 00:19:42.039 That's an em dash. I've been doing that since the nineties. 00:19:42.039 --> 00:19:45.079 I used em dashes before they were uncool. 00:19:45.079 --> 00:19:47.079 I guess maybe they were never cool. 00:19:47.079 --> 00:19:48.519 So I know how to use an em dash. 00:19:48.519 --> 00:19:51.720 So just because you see an em dash in any of my content does not 00:19:51.720 --> 00:19:53.639 mean that it was written with an AI. 00:19:54.105 --> 00:19:58.664 But now the way that this is working for me is great because as a 00:19:58.664 --> 00:20:02.904 single dad, homeschooling my son, and running my own business, my 00:20:02.904 --> 00:20:05.384 time is very valuable. 00:20:05.384 --> 00:20:09.380 And I really don't wanna spend it on stuff like rewriting my 00:20:09.380 --> 00:20:11.700 content into an article format. 00:20:11.700 --> 00:20:15.859 That's the kind of thing that AI is great at doing because it is 00:20:15.859 --> 00:20:19.779 my content, not the AI's content. It's not AI slop. 00:20:19.859 --> 00:20:23.434 It's my slop, but I wouldn't even call it slop. 00:20:23.434 --> 00:20:28.154 It's my content that the AI then is restructuring, and not just 00:20:28.154 --> 00:20:29.835 restructuring on its own. 00:20:29.835 --> 00:20:34.240 It's restructuring with the guidance of my tone of voice, how I 00:20:34.240 --> 00:20:38.720 speak in addition to giving it the actual outline that I use so 00:20:38.720 --> 00:20:41.920 it knows not to make a whole bunch of subpoints that didn't exist 00:20:41.920 --> 00:20:46.319 or give me a whole new outline, but it recognizes my outline just 00:20:46.319 --> 00:20:47.279 like PodChapters does. 00:20:47.585 --> 00:20:51.744 And it then uses my tone of voice in the writing and uses my 00:20:51.744 --> 00:20:56.944 content. It is simply reformatting my content into an article. 00:20:56.944 --> 00:20:59.904 And I think it does a much better job than these systems that 00:20:59.904 --> 00:21:03.970 automatically take your transcript and turn them into articles or 00:21:03.970 --> 00:21:07.650 blog posts because those things are missing the tone of voice. 00:21:07.650 --> 00:21:10.690 They're missing some of these other things that I've learned how 00:21:10.690 --> 00:21:12.289 to do with the AI. 00:21:12.369 --> 00:21:15.174 And my tool for that, by the way, that I'm using, it's not 00:21:15.174 --> 00:21:16.695 something I've made for myself yet. 00:21:16.695 --> 00:21:19.095 I've thought about maybe making something like this, but then 00:21:19.095 --> 00:21:21.654 again, there are so many other tools that try to do something 00:21:21.654 --> 00:21:25.815 like this that, again, it would be an education issue for another 00:21:25.815 --> 00:21:29.109 product to try and explain to people why my tool does things 00:21:29.109 --> 00:21:31.829 radically different than others and why they should use my tool 00:21:31.829 --> 00:21:36.069 instead. So what I'm using is Magai. It's my favorite AI toolbox. 00:21:36.069 --> 00:21:39.349 I am a paying customer of Magai. I'm also an affiliate. 00:21:39.464 --> 00:21:45.464 So if you visit the audacitytopodcast.com/magai, that's Magai, 00:21:45.625 --> 00:21:46.904 that is my affiliate link. 00:21:46.904 --> 00:21:49.304 I do earn a commission if you sign up through there. 00:21:49.304 --> 00:21:53.400 And I do highly recommend Magai because it is a super toolbox of 00:21:53.400 --> 00:21:57.480 AI tools. You've got GPT in there. You've got Opus. 00:21:57.480 --> 00:22:01.400 You've got Gemini. You've got DeepSeek. You've got MiniMax. 00:22:01.400 --> 00:22:02.600 You've got Kimi. 00:22:02.600 --> 00:22:06.600 You've got all of these language models as well as image and 00:22:06.600 --> 00:22:07.480 video models. 00:22:08.174 --> 00:22:11.455 So these are the 3 major changes I made to my podcasting 00:22:11.455 --> 00:22:15.855 workflow, and it just feels so much better to me. 00:22:15.855 --> 00:22:19.535 Number 1, I'm using PodChapters for chapters and transcripts. 00:22:19.535 --> 00:22:23.149 Number 2, I'm back to speaking from the outlines instead of using 00:22:23.149 --> 00:22:23.710 scripts. 00:22:23.710 --> 00:22:28.190 And number 3, I'm making the episode articles with my outlines 00:22:28.269 --> 00:22:30.589 and a specially trained AI. 00:22:30.669 --> 00:22:33.389 If you would like to check out these links, like to PodChapters 00:22:33.389 --> 00:22:36.944 or to Magai, then please visit the notes, a simple tap or swipe 00:22:36.944 --> 00:22:39.664 away, or click the link from the chapters. 00:22:39.664 --> 00:22:42.065 And now that I've given you some of the guts and taught you some 00:22:42.065 --> 00:22:45.265 of the tools, it's time for you to go start and grow and maybe 00:22:45.265 --> 00:22:48.464 even consider changing your podcasting workflow for your own 00:22:48.464 --> 00:22:51.890 podcast for passion and profit. I'm Daniel J. 00:22:51.890 --> 00:22:54.369 Lewis from theaudacitytopodcast.com. 00:22:54.369 --> 00:22:57.730 Send me your feedback or podcasting questions at podcast feedback 00:22:57.730 --> 00:23:00.930 dot com slash audacity. And thanks for listening.