Mind Readings: Making a Podcast with Generative AI, Part 1

In the last couple of weeks, folks have been playing around with Google's Notebook LM as a way to create podcast style audio from documents. Give Notebook LM a document. I'll pull up uh Notebook LM on uh on my second screen here and give it a document and it can create an audio uh sample. So I'll go to the notebook guide here and it can create a deep dive conversation. This uses Google's audio LM uh system through Google TTS, pretty sure, using their journey uh voices.

My guess is that Gemini, which is the engine that powers Notebook LM, creates a diarized transcript of what it's going to say of the summary with SSML tags and then passes that to Google TTS, which generates the very realistic sounding voices. Here's the problem with this. It's a cool tool. It is a cool tool. It creates a seven to nine minute podcast style discussion.

You have no control over it. You just hit the generate button and it creates a thing. And that thing is fine. It's a nice summary, but it has you have no ability to edit it. You have no ability to control it, and it has none of you in it.

So while I was out for my run today, I thought to myself, what if we were to create a way for you to do an audio podcast style with generative AI using chat GPD's advanced audio mode, and have it be interesting, have it be something that might be worth listening to because it wouldn't be machines talking, it'd be you being interviewed by a machine. How are we gonna do this? Well, this is gonna be a multi-part series. We first have to create the instructions for chat GPT to be able to uh interview us, and then we have to deploy those instructions on our device, and then we have to be able to uh you know get a conversation going using the advanced audio mode. So, prerequisites.

The hardest part of this, believe it or not, uh, is getting the audio set up. So I have here, and I'll see if I can tilt my camera down. I have the RodeCaster Pro, and I have my iPhone connected to that via Bluetooth. Whatever your audio setup is, you need to get audio from your phone to some kind of recording interface. It could be uh soundboard, it could be straight into your computer, but you need to get your audio captured from your device and from you.

So I'm using my RODCaster, I'm using my um my sure SM7B here, which is tied into the Rodcaster. So all of the audio for this is coming through one port. You could do it with multiple ports, plenty of people do, um, but it's that's gonna be the hardest part. And I can't give you much guidance on it because I don't know what kind of hardware you have, but that's part one is get working audio from your device to um to your desktop. If you can't do that, if you just don't have the hardware or whatever, then the workaround is to take your device and turn on screen recording mode, which is I have it set in my uh thing here, and what this will do is it will record all the audio coming off your device, and then you have your audio being recorded on your laptop or whatever, and then you're gonna need to sync it up in post-production in the audio editor of your choice.

You'll have to bring the two tracks together. So you'll probably need to you know do the usual like clap your hands and stuff to make sure that you can line up the two audio tracks. But that's that is the hardest part. It took me like 45 minutes to work out all the different combinations just from my setup. Um when you do it right, it works pretty well.

So that's part one. Part two, we need to go to chat GPT now and start asking it questions about how to do interviews. So let's flip over to chat GPT, and we're gonna start with the the priming process. So if you're not familiar, go to trustinsights.ai slash payer, P A R E, and this will give you the layout of what we're gonna do. We're gonna start with saying you're an interviewing expert in the style of Sean Evans from Hot Ones, Larry King, Barbara Walters, etc.

What do you know about conducting a great interview, particularly for a podcast? Okay, so we now got the first step of the pair process. Let's now ask it what are some common mistakes made by less experienced interviewers and podcasters when conducting guest interviews. Okay, part two is done. Now we're gonna follow up with sort of a refresh and say, what are some expert tips and tricks for interviewing guests on a podcast that we have not discussed yet?

Okay, we have now completed the priming process. We've asked the model, what do you know about a topic? What are some mistakes about the topic? And then what are some expert tips and tricks we haven't talked about yet? This priming process is super helpful for getting the tools like ChatGPT to understand the context of what it is that we're talking about, because we want we wanted to have a wide base of knowledge, and we could have provided all this information ourselves, and perhaps we should, um, if you have a particular interviewing style.

However, this is an easy way for uh to let the tool do a lot of the typing for you. So, this is the conclusion of part one. We have connected audio, hopefully, and we've done the priming process. In the next part, we're gonna create the interviewer. So stay tuned for that.

If you enjoyed this video, please hit the like button. Subscribe to my channel if you haven't already, and if you want to know when new videos are available, hit the bell button to be notified as soon as new content is live.