Real quick before we get started. I want to tell you about a brand new newsletter I'm launching called Podcast Workflows. Each week I'll do a deep dive on how a popular podcaster creates their show. From start to finish, from processes to tools. Then, I'll tell you how you can apply what they do to improve your own podcast workflow.
You can sign up over at [podcastworkflows.com]. One breakdown delivered to your inbox weekly. Learn the tools and processes used by top podcasters and reclaim hours of your life, every week. That's [podcastworkflows.com]. Sign up today, for FREE.
I was a Freelancer, Web Developer and Programmer since 14 years old, before pivoting to Podcasting and Automation. And we, programmers have a saying when it comes to the quality of what our work produces, garbage in, garbage out. That means your output is a function of your input. And this is true all the time, right? If you eat like garbage before a run, your run is going to be garbage. If you stay up all night out drinking the night before, and then try to do your job the next day, you're going to do your job poorly. And if you write code that doesn't accept good inputs, then you're not going to get good outputs.
When it comes to tools like ChatGPT, the better your prompt, the better the answer you will get. And when it comes to using AI to repurpose your content, the clearer your content, the better the assets AI generates.
Now, a couple of episodes ago, or in a previous episode, I talked about how generative AI tools can help us podcasters. I don't think synthesized voices are going to be the place where AI can help us the most. It's going to be in places like research, but also repurposing. And there are some tools out there like Castmagic that can help us. However, If your inputs are not good, then Castmagic and Cap show with their outputs are not going to be good either.
So today, I set out to answer the question, “Can Generative AI Help us be Better Podcasters?”
Stick around to find out.
Welcome to the Profitable Podcaster where I help coaches, course creators and authors launch and grow their podcasts to help them build authority, generate more leads, and sell more through actionable advice and expert tested systems.
I'm your host, Joe Casabona and I've been podcasting for over 10 years. I've generated millions of downloads and hundreds of thousands of dollars from my shows. I'll teach you everything I know here on The Profitable Podcaster.
Okay. So what do I mean by garbage in, garbage out? How can generative AI possibly help us make better, make us better podcasters?
I've been experimenting with Castmagic over the last few weeks, and something became very clear to me.
When I speak off the cuff, sometimes my point is not obvious or put a different way. When I speak off the cuff, sometimes I'm not very clear.
Now, I won't lay too much credit at the feet of generative ai, but when I have it transcribe and subsequently summarize my thoughts, it seems to focus on one to two things. Presumably the things that it understands the best. These could be the things I said the most. These could be the things that I mentioned at some point, right? It could be what I have placed at the assumed climax of the episode.
Now, I'm not an expert in large language models or LLMs for short, but the basics are this: They take in a ton of text-based data, and they use math to associate the discreet words from those texts.
So for example, it might recognize due to statistical analysis that the words I want to go to, more often end with the words: Paris, France, then Cheyenne, Wyoming. Sorry Wyoming and…
Sorry. The fine folks of Cheyenne if I'm saying that incorrectly. All of that is to say, LLMs likely understand how people tell stories and make assumptions about how we organize our own content.
Now, I decided to ask ChatGPT by way of Raycast.ai, what makes a good story? And here's what it said, “My exact prompt, I'll tell you my exact prompt and you can see screenshots over in the article linked in the show notes.”
What is the structure of a good story? ChatGPT said this, “A good story typically has a clear, beginning, middle, and end with a well-defined plot, interesting characters, and a compelling conflict or goal. It often includes a strong narrative arc, emotional resonance, and themes that resonate with the reader or audience. Additionally, effective stories often incorporate elements such as foreshadowing, symbolism, and imagery to enhance the overall impact of the narrative.” Then, so that was what ChatGPT, said.
Then I asked it the most important point of the story. Again, my prompt was, what's the most important point in a good story? It said the most important point in a good story is often the climax, which is the highest point of tension or conflict in the narrative. This is where the main character confronts the central problem or challenge and faces their greatest obstacle.
The climax is a pivotal moment in the story that often determined the outcome of the plot and has a significant impact on the characters and their relationships. A well executed climax can be emotionally satisfying for the audience and leave a lasting impression.
Then I said, “When does the stories climax usually take place?”
The stories climax usually takes place towards the end of the narrative after the rising action has built up and the tension and conflict, and just before the falling action begins to resolve the story's conflicts and bring it to a close.
And while Castmagic, (that's the end of that quote, by the way) and while Castkmagic doesn't always pick what I talk about at the end, it does pick a point after I've built some momentum. The problem is that that's now not how I structure these episodes. I usually put the most important information up front. Notice I'm not doing that for this episode, by the way. While there is a place for that, putting the most information up front, I mean like social media, it doesn't create compelling content like a story does.
On social media and short form oriented platforms, we want the information as soon as possible. We want the quick hit quickly. but the problem is that we are storytellers. There's a clear difference between the popular podcasts and the struggling one.
A story (not in the quot) “Hero rescues the people in trouble” of sort of sense. But there is still a clear beginning, a conflict, a climax, and a satisfying resolution.
And if you subscribe to the hero's journey, there is still a hero, the listener, and a host, the guide, or maybe the guest, but usually it's the host. For example, on this show, I might tell a story about how I had a client. The hero struggling to stay consistent.
In the beginning, she starts the podcast diligently producing an episode each week. But then she falls behind after being sick and having to unexpectedly take a week off.
This is the conflict. So she hires me the guide to help her, and we set up a few automations that save her two hours per week. There's the climax. Now, she can spend those two hours creating a back catalog of episodes saying one to two months ahead. That is the satisfying resolution.
This is much more compelling than me talking about how you need to automate parts of your podcast, right? I am illustrating that point with a story. A success story specifically.
And doing a little bit of planning from the beginning can help us create better episodes, which then creates better content for repurposing on other platforms.
So knowing all of this, the structure of a story, that generative AI makes some assumptions based on our inputs, and that the better the input, the better the output.
How does knowing all of this help us? What can we do with this information? If we want to leverage generative AI for repurposing, especially, we need to give it better inputs, garbage in, garbage out. That means doing a little bit of planning upfront. And I think there are two ways that you can do it:
1. You can plan the show on your own. Outlining, outlining, creating Pseudos scripts and building a narrative around each episode. Remember, we need to lean into the story.
2. Use AI to help you plan and organize your episode, giving it a topic, and then crafting a prompt to help you build a better episode. Here's an example of that. Again, I'm going to read my prompt and then I'm going to read what ChatGPT said.
The prompt. I have a solo podcast called The Profitable Podcaster where I help podcasters improve their workflows and processes to waste less time so they can focus on creating content to make money and build authority. Do you understand this is important? Cuz I wanted to read and remember that because ChatGPT, it's an ongoing chat. It remembers what you just said. So it gives me confirmation that it remembers that.
Then I said, I want to create an episode for this podcast called Five Tools I Use to Organize My Podcast where I talk about Airtable, Bear notes, Google Docs, Castmagic and make.com.
Can you create an outline for that episode? That also creates a compelling narrative for the listener. It then goes on to create this outline telling me to add stories and things like that. But you can also feed it and outline and ask to improve it.
So here I say, again, these screenshots are in the blog post. I'll link them in the description or in the show notes. I'm creating a podcast episode where I help listeners design a workflow to help them plan, record, and publish their own podcast episodes. I'd like you to take the provided outline and make improvements to it. Restructure if you need to. Add topics and bullet points and add relevant anecdotes. And then the full outline.
So I also include the pretty long response, cold open, share a story, share a personal anecdote. This one was just okay, but then I asked it to write a narrative based on what I just said earlier about my client who needed help. So it gives me a six point outline That basically goes through the arc of the story, which I think is pretty compelling, telling me to start with the hook that grabs the listener's attention.
Have you ever struggled to stay consistent with your podcast? Then I introduce myself and the client explaining the problem that she was facing using specific examples, Describe the process. We went through to solve the problem, highlight the key benefits of my solution, wrap it up with a call to action and end with a memorable closing statement.
Leveraging AI isn't just about creating content we normally wouldn't create. It's about helping us create better content. That means using it for both input, researching, organizing, crafting stories, and output. Taking what we've created and repurposing it for other platforms. When you create better inputs, your outputs will be so much better.
That means leverage generative AI to help you craft a good story. A good narrative for your podcast. If you look back on this, if you re-listened to this episode, You'll notice I started with an anecdote. then I set up the problem, right? So if you are the hero, I have set up a problem for you. and that is that generative AI doesn't always produce great output.
Based on our input, we go through a journey where I explain to you how a story works. The climax is where I tell you that we are storytellers and we need to leverage that to create good content. And then the satisfying conclusion is how to use chatGPT and other tools with that knowledge that we are storytellers.
So I want you to think about that. This is also the first time I've tried a format like this. So let me know. Was this a more compelling episode than previous ones? I'd be really curious. I'll be paying attention to the stats. I'll also be paying attention to the output I get from Castmagic on this to see if it's better than previous episodes.
But that is it for this episode of The Profitable Podcaster. I hope you enjoyed it.
If you are leveraging generative AI for your podcast, let me know. I'm @jcasabona on Twitter, or you can fill out the form at [profitablepodcaster.fm/feedback] if you want to get one deep dive into a popular Podcasters Workflow, their process every week. Sign up for my newsletter over at [podcastworkflows.com]. But that's it for this episode.
Thanks so much for listening. And until next time. I can't wait to see what you make.