Subscribe to AIMinds Newsletter
Stay up-to-date with the latest AI Apps and cutting-edge AI news.
Subscribe
Share this guide

About this episode

“We're approaching this as we want to be the premium product in podcasting, Podcast AI, in the same way that OpenAI is the top series of models that you can use for LLMs.”

— Edward Brawer

Edward Brawer is the CEO of Podcast AI. He is a seasoned software developer, born and raised in Toronto. Exposed to the world of technology from a young age, he began learning to build websites and applications for both Mac and Windows, long before terms like front-end and back-end development became commonplace. He has watched as the industry evolved over the years. Notably, Edward has contributed to the medical field, developing nationally used apps while offering his skill set to consultancy roles within the Canadian healthcare sector.

Listen to the episode on Spotify, Apple Podcast, Podcast addicts, Castbox. You can also watch this episode on YouTube.


In the very first episode of AI Minds, we had Edward Brawer, the CEO of Podcast AI, sharing his journey from building medical apps to venturing into podcast automation using AI.

From founding his startup to catching the attention of Jason Calacanis through viral tweets, Edward highlights the innovative features of Podcast AI and the aim to revolutionize podcast production and content creation. With insights into the challenges and exciting developments in AI technology, this episode offers a fascinating peek into the future of podcasting.

Here are the key takeaways from his conversation with Demetrios:

  1. Automation Revolution: Edward's mission to automate every aspect of podcasting is a game-changer, saving producers countless hours and revolutionizing content creation.

  2. Building in Public: The power of viral tweets and building in public not only helped attract attention and investment but also shaped the development of Podcast AI's features.

  3. Using AI Innovatively: From transcriptions to creating synthetic content, Podcast AI leverages cutting-edge AI technology to enhance the entire podcasting process, providing top-tier user experience.

If you want to learn more about how Edward and his team are revolutionizing podcasting with AI, I invite you to check out their full conversation!

Fun Fact: The company's slogan, "reclaiming your time," was inspired by a tweet from Jason Calacanis, expressing his intent to reduce his podcasting commitments.


Show Notes

00:00 Startup learned lessons, moving to California quickly.
04:15 Parody of all in podcast goes viral.
08:14 Differentiation vital for AI companies in public.
11:43 Podcasters spend a lot of time distributing.
13:41 Using AI for complex tasks requires layering.
17:27 Automating podcast tasks saves time for creators.
21:51 GPT-4 access was crucial, and finally improved.
23:12 Expresses gratitude and invites others to join.


More Quotes from Edward

“We eventually want to go A to Z on podcasting. I mean, it's in the name 'Podcast AI'. But if you start, there's sort of pre production, which is all the scheduling stuff. So everybody showed us the spreadsheets that they use, and we want to do a product for that. And then there's production, which is the actual recording, which is frankly a commodity. There's Zoom, there's tons of ways to record a podcast. Where we start right now is the post processing, post production, meaning you've recorded the mp3 or the video file, you upload it into Podcast AI.”

— Edward Brawer

“We're actually generating blog posts that go with that viral moment, including LinkedIn, Twitter/X, Threads, Instagram, TikTok, YouTube short, just generating everything.”

— Edward Brawer

“For Podcast AI, everything starts with the transcript, right? So you're uploading that episode and then you're hitting transcribe or it's automatically doing it for you. And that's the basis on everything because every other LLM is fed from that transcript. So the fact that Deepgram does the speaker identification, that's absolutely critical. And that lets us rapidly identify the speakers, the hosts and the guests.”

— Edward Brawer

Podcast AI is also featured on our AI Apps page here!


Transcript

Demetrios:

All right, welcome, everybody. We are here with Edward, who is the creator and CEO of Podcast AI. A Toronto native, went to the University of Waterloo, but did not go for computer science, who went for Biology because he already knew how to do whatever he needed to do with the computer. Edward, it's great to have you here and I'm looking forward to dive into what you're doing with Podcast AI, how you found building with AI in general to be. But before we get into any of that, I'd love to hear a little bit about your background and what you've been up to until now.

Edward Brawer:

Yeah, pleasure to be on the show. Born in Toronto from fairly early age, like in the late nineties, doing websites, you know, learning how to write apps for, for Mac, for Windows. You know, it's kind of funny, like in software these days, everybody's talking about, are you front end, back end. I was doing stuff pre that being a thing. And it's been pretty exciting just seeing how software has kind of evolved. Did a lot of medical apps. So I was doing some consulting, doing medical apps in Canada, some nationally used apps as well.

Edward Brawer:

And in 2019, me and my best friend, Sean, we banded together. He was my best friend since grade nine. And we did our first startup that was sort of in the creator space, but then everything changed with we had heard of GPT and logged into OpenAI for playing around with GPT-2 it was kind of interesting. You'd give examples of YouTube titles and it would hallucinate more of them type thing. It was kind of useful, but you could see how it could become useful. But it's really when chat GPD came out that changed the game. And Sean and I, we were like, okay, pencils down. Stop.

Edward Brawer:

Everything we're doing, we have to do this. This is the biggest thing we've seen in 25 years, 30 years.

Demetrios:

Time to pivot. Yeah. So you were in the creator space. You're now still kind of in the creator space with what you're doing with Podcast AI. Can you break that down a bit?

Edward Brawer:

Yeah. So before our previous startup was doing something where it was trying to combine, let's say a YouTube and a Patreon together. And it's a very different business because we learned so much. We learned that you can't fight network effects. That's really one of the big lessons. And there's a lot of other lessons that we learned, especially wanting to build a venture backed company and being in Toronto, realizing that the value of ground game, hence we're working on moving down to California where everything's happening. But yeah, it's kind of amazing how fast we built up podcast AI. We only started in May, and we built this thing at breakneck speed.

Edward Brawer:

It's the best piece of software I've written. And yeah, AI is just such a big part of that.

Demetrios:

In every way a culmination of all those past events now has led you to writing the best software of your life.

Edward Brawer:

Exactly. All roads are converging here.

Demetrios:

Yeah. Well, break down some of the stats. What have you got for us as far as users and what you're doing? Maybe GPT calls or transcribed hours, all that fun stuff. So we get an idea of what you're working with.

Edward Brawer:

So let's say we have 25 customers right now, paying customers. We got our first customers in September. We took 19 sales calls in September, October 15 of those, we closed on the call, which was pretty bananas.

Demetrios:

That's a good signal.

Edward Brawer:

Yeah, to sort of back up. We got into this by building in public. So originally it was me playing around with the eleven labs API and essentially creating a parody of the all in podcast. So I tweeted that and ten minute parody. And the sort of background idea was that the cast of all in was reborn as ais. They had ended an episode joking about like, or started one joking about, oh, you're going to become an AI or something. So I basically made that. It went viral.

Edward Brawer:

It got retweeted by them. I did six in total. But going through it, people were like, is this real? Half the people thought it was real, and half of them realized it was me scripting the show and using their voices. But we realized, hey, let's build a company right now. Because what was happening with AI was just absolutely insane.

Demetrios:

You had the momentum.

Edward Brawer:

Yeah, we had the momentum, like just the attention. Second time founder, you realized distribution is everything. You can have the best execution, but if there's no distribution, there's nothing. So we realized we got an amazing name, podcast AI. I think you can't really do better for what we're doing.

Demetrios:

No, it's just you up one night, like, I wonder if it's available.

Edward Brawer:

That was Sean. We were looking for domains related to the other company, and Sean had found a service that was giving these domains for sale. And we were just talking about this idea of doing an AI company around podcasting. And I forget which one of us were like, try podcast AI. And boom, it was available for sale. We bought it like on the spot.

Demetrios:

Hundreds of thousands of dollars later, not even that much.

Edward Brawer:

I think it was underpriced.

Demetrios:

Wow.

Edward Brawer:

It was 10,000.

Demetrios:

No way.

Edward Brawer:

I think a steal. I think a steal.

Demetrios:

Yeah. Especially for doing what you are doing, which is so clear for podcasting using AI. I love that. All right, sorry I derailed the story, but keep going.

Edward Brawer:

Well, no, it's exactly that. We decided, okay, we're going to build a company that is going to automate podcasting. The plan, the mission is really automating everything a to z, making it save human producers hundreds and hundreds of man hours or person hours. And that's the mission. And even creating, like getting to the point of creating synthetic content, we can generate ad reads in the voice of the host, ad libbed about any sponsor and call to action. And it's amazing. There's nothing like showing that demo. It's a really ambitious project.

Edward Brawer:

And we got into Jason Calicanis's first, his founder you program. We got a small investment check through. At the end of that, 10% of the companies get that check. And then we got invited into the accelerator program early September, and the rest is history.

Demetrios:

So was that because of these viral tweets? Be honest. And that you buttered them up with?

Edward Brawer:

That's the start. You have to get on people's radar. That's the thing with raising VC, and that's the thing we didn't understand the first time in late 2019 when we started the previous startup. It's that you have to network yourself in. And vcs, they just have so much incoming, there's so much noise that you have to introduce some signal and get on the radar, and you just have to impress them with something, show them something amazing. And that's the secret. Yeah.

Demetrios:

And especially when you're building with AI, because there are so many companies out there right now doing something in this space that to differentiate yourself is a huge value when it comes to vcs looking at you and saying, oh, yeah, I've heard of them because I've seen some viral tweets, or I've heard of them because I've seen what they've been doing. They've been building in public, as you say. And I really like this notion of building in public. How have you been taking that? Are you going as far as sharing all of your customers, sharing your revenue numbers, all of that kind of indie hacker building in public? Or is it more like, hey, check out this cool feature. We just threw this out there. Do people like it? Do they not?

Edward Brawer:

Screenshots of cool features? Part of it is the product we're doing. So for example, we'll turn a podcast into a website, and the website will have statistics on the podcast, all the links. So, for example, this weekend, startups, that's like 1800 plus episodes by Jason Calicanis. We now power this, weekendstartups.com. So that's just a beautiful demo of what we can do. All the transcripts are in there, powered by deep gram. There we go. Table of contents that we generate all that great stuff, all the distribution points, all the advertisers, we automatically detect the sponsors and rotate those through the transcript as like calls to action.

Edward Brawer:

And finally, an AI chat with AI versions of the host, trained on all the past episodes.

Demetrios:

So you're chatting with the host. Yeah. Break down a little bit more about what podcast AI does so that we can understand all of the different features.

Edward Brawer:

Yeah. So we eventually want to go a to z on podcasting. I mean, it's in the name podcast AI. But if you start, there's sort of pre production, which is all the scheduling stuff. So everybody showed us the spreadsheets that they use, and we want to do a product for that. And then there's production, which is the actual recording, which is frankly a commodity. There's Zoom, there's tons of ways to record a podcast. Where we start right now is the post processing, post production, meaning you've recorded the mp3 or the video file, you upload it into podcast AI.

Edward Brawer:

And then we generate the description, the title, automatically put the episode number, generate the chapters, do the whole transcript. Speaker identified. Again, thanks to deep Graham, we generate the key points, key takeaways for the podcast, all those show notes type things we generate right now, viral moments from the episode. Top ten viral moments. And we're actually doing now we just released this, generating blog posts that go with that viral moment, including LinkedIn post, Twitter Slash, xthread, Instagram, TikTok, YouTube short, just generating everything. And the roadmap is actually to be able to post those directly onto the social accounts so that we really are automating the pipeline a to z. Yeah.

Demetrios:

Saving so much time. I do know that that is one thing that a podcaster spends a ton of time on is just the data transfer and taking the video, the edited video, downloading it, then uploading it to YouTube, uploading it to Spotify or your podcast distribution center, then adding the description. And the description for Spotify is a bit different than YouTube because YouTube, you can do different things with it, adding all of the chapters, adding all of the links and the different things that you talk about. So it's show notes in that you, because I think this is a really hard problem that I would love to dig into. Are you automatically grabbing links? So if we say, hey, you know, what is really cool is the way that Tim Ferriss does show notes and adds links. And you can see that on tim.com slash podcast. Do you automatically pick that up, grab it, and then throw it into the show notes? Because that seems like it's a really hard problem to do. And I would love it if somebody did that.

Edward Brawer:

So that is literally a top feature request right now, and we started work on it, so you will probably see it in the product within the month.

Demetrios:

Well, realistically, how can you make that happen? Because a lot of times I just made it really clear for the transcript to understand what the link is. But if I was saying something like, oh, you know, who does podcast show notes really well is Tim Ferriss. You would need something to go out and find Tim Ferriss's podcast URL and then show different show notes from his podcast URL, which seems like a very hard problem. And you may need some kind of autonomous agent in there. How are you looking at attacking that type of problem?

Edward Brawer:

So it is hard and it isn't. So basically with AI, the crazy thing is how easy it is to do something amazing in one call to the LLM. But to do anything beyond that, what you really want to do is layer calls to an LLM. So you don't quite need an autonomous agent, but what you need is sort of a procedure which is really doing what humans do, right? Like we'll take one pass at something and then a second pass and a third and a fourth and a fifth, and that's how we refine work product. The app itself, the back end really needs to be doing the same thing. So what we would be doing is first pass detecting what is possibly a link for the show notes or intent for something to be a link in the show notes, and then on a second pass actually attempt to retrieve that from the intranet and determine what the link is. So through a few passes you can actually do stuff like that. It's just hard because you have to do it right.

Edward Brawer:

It's not as easy as a one shot LLM call, but imminently doable.

Demetrios:

Yeah, I imagine you have to think about costs and how much is this going to add to the end user experience. This case, I think it's very clear. Like, this would be incredible. It's obviously one of the top feature requests that you have. But then on other features you have to weigh out those pros and cons. Like, is this worth another LLM call? Is it going to add that incremental value? Or is it going to be like hitting it out of the park for the end user experience? And so it makes it worth it to add that 0.3 cents per token or whatever it may be, whatever the cost is by the time this podcast comes out, because it's constantly changing. But how do you look at that? How do you think about those trade offs on the feature that you're introducing, but on the back end, the amount of cost that it's going to cost you, and it's almost like your cost of goods or cost of services is going down. That profit margin that you have is going down.

Edward Brawer:

Yeah. So the way we approach this when we started is in theory, the best way to price your product is to determine the value, and then you price according to the value. But to keep it simple, when we started, we just said, okay, we're going to figure out what our costs are. We're giving on each subscription a number of credits. And every action that costs us credits that costs us money, we basically deduct from credits that you have to use.

Demetrios:

Right.

Edward Brawer:

So we basically make it so the user is budgeting for themselves and deciding, okay, what's valuable. And I think that those show notes will be valuable. And also our plans are pretty generous on the credits, so I doubt anybody would be bumping against the limit. It's really just a guardrail. So there's that. And also, look, we're approaching this as we want to be the premium product in podcasting, podcast AI, in the same way that OpenAI is the top series of models that you can use for llms. So that's our intention and doing that work. And here's something that's similar to do, right, and similar pain point in terms of intensity for users guest research that is labor intensive, we can automate that in the exact same way.

Edward Brawer:

So that kind of becomes that pre recording step that's right next to the scheduling. That's also something we intend to do.

Demetrios:

Yeah. The amount of steps that is involved in a podcast, when you break it down, it is not like any of them are very difficult to do, but they are just tedious. And so you saying, you know what, we don't need a genius to do this. We could probably automate it with a bouquet of zapier and LLM calls and maybe some chain together LLM calls. However you're doing that and some, right, some calls to the different APIs like Deepgram. And so if you are able to do that and take, you're giving me back time as a podcaster, you're really opening up my ability to say, okay, now I don't have to worry about the scheduling or the research. I just got to show up. And that's one of the things that I am a big proponent of, is that with the podcast, I want to figure out a way to make the process so simple that I just have to show up, because that's what I enjoy doing.

Demetrios:

Right? I enjoy talking to people. And so if that is the end goal, I'm all for that, and I'm really excited for what you're building.

Edward Brawer:

Yeah, 100%, basically reclaim. So again, Jason had tweeted something like, I'm reclaiming my time. I'm going from seven podcasts a week down to four. And when we were building the company, that sort of became our slogan, like, let's let people reclaim their time and turn them into ten x producers. So, yeah, that really is the thing. And with podcasting, it's like, there are a lot of steps, but the truth is, podcasting can be as bare bones or as high production value as you want. So for someone who really wants bare bones, record a zoom and flip it to YouTube. That's it, right? You don't even have to describe anything.

Edward Brawer:

You just put a title and you're done. But that's not going to do well. What you want is the production quality. You want chapters, you want summaries, descriptions, you want all of that good stuff. You want a nice show website that's completely automatic.

Demetrios:

You want to get the word out. Yeah, exactly.

Edward Brawer:

So you really have to up the game. And that's what we've kind of been seeing with podcasting, right? Everybody's upping their game, and the idea is, for the least work possible, make it so someone can up their game with podcast AI up to that top level.

Demetrios:

Well, man, I appreciate this. I want to leave with one final question, because you are building in the space, and AI is so new. You're doing all different kinds of things with AI, whether it is transcriptions. So you're kind of doing the whole pipeline, I would say not just when you look at the podcast pipeline, but when you look at there's audio coming in, it's being transcribed, you're taking insights from that transcription, and then you also have the ability to create audio on the other side of it, so you can go text to speech. And so for me, that's basically the whole gambit now, what are some of the main challenges that you have faced while building with all of these different new technologies?

Edward Brawer:

So the technology itself is unbelievably simple to use. I'll just give you a few friction points that might have happened. That did happen. So one was you need a vector database, and because you need a vector database, we had to switch from MySQL to postgresql. So that was a little database change that happened very early on because you get Pgvector, which lets you do those vector searches. So that was one thing. The second big issue was with OpenAI, getting access to rates like tokens per minute and stuff like that. That was super important for us.

Edward Brawer:

Getting access to GPT four really early on was super important to us, and it's sort of hard to wiggle yourself into that. Thankfully, we recently got a really big limit increase. But yeah, that was a big pain point. But it's interesting how the actual working with the LLMS is just such a pleasure, and probably literally the easiest one is Deepgram, because nice. For podcast AI, everything starts with the transcript, right? So you're uploading that episode and then you're hitting transcribe or it's automatically doing it for you. And that's the basis on everything because every other LLM is fed from that transcript. So the fact that Deepgram does the speaker identification, that's absolutely critical. And that lets us rapidly identify the speakers, the hosts and the guests.

Edward Brawer:

And then everything else is from that. The chapters are done from the transcript, the summary is done from the chapters. So that's like a little cheat to go faster. So really the root of it is the transcript. And I have to say, deep Graham, it's just a pleasure to work with. There's no rate limits. It's super fast. It's like 10 seconds for a 1 hour podcast.

Edward Brawer:

It's unbelievable. Just amazing.

Demetrios:

I love hearing that. And it's also awesome to have you as part of the startup community that we are rocking. And I will say right now, if anybody else out there listening would like to join the startup community, please reach out or just go to slash startup and fill out the form. We are open and we are accepting people still. So, dude, Edward, it's been a pleasure. I really thank you for coming on here and doing this podcast with us. I feel like it's a little bit meta. We are having a podcast talking about podcast AI.

Demetrios:

And later on I think we're going to get to see you using podcast AI on this very podcast. So it can't get more meta than that, and we will end it there.

Edward Brawer:

Awesome. It's been absolutely pleasure to join you here. And, yeah, I love what you guys are doing. And you guys are the backbone of transcription, I think.