That’s right. Content creators need to understand how artificial intelligence will drive podcasting in 2023 and how these new tools will help their production and business needs.
So, happy new year to you. Let’s get started.
How can artificial intelligence tools help podcasters?
I posed this question to ChatGPT, the OpenAI product that last month caught the world by storm. But to get you warmed up, I asked ChatGPT to first define itself.
“ChatGPT is a computer program that is designed to carry on a conversation with a human user. It uses advanced artificial intelligence techniques to understand what the user is saying and generate appropriate responses. ChatGPT is designed to be used in chatbot applications, which are programs that allow users to communicate with computers through a chat interface. ChatGPT is able to understand and respond to a wide range of inputs and can carry on a conversation in a way that is similar to how a human would.”
Pretty good, right?
What’s important is that ChatGPT can interpret your requests to write anything from simple to complex copy. I’ve asked ChatGPT to write news articles, scripts, social media posts, and business plans. It has yet to disappoint me in a context that I think would be useful for podcasters.
And it’s improving!
Last month, when I posed this question about its use for podcasting, it gave me a very practical answer, which I’ll share with you here.
“Language models like myself can be used in a variety of ways in the production of podcasts. Some possible uses include:
- Transcription: Language models can be used to automatically transcribe audio recordings into text, which can be useful for creating written transcripts of podcasts.
- Summary: Language models can be used to summarize the main points or key takeaways from a podcast episode, which can be useful for creating summaries or show notes.
- Scriptwriting: Language models can be used to assist with the writing of script for podcasts, by generating ideas or suggesting alternative wording for certain sections of the script.
- Voiceover: Language models can be used to generate synthetic voiceover for podcasts, allowing for the creation of custom voiceovers without the need for a human voice actor.”
As I sat down to write this, it gave me a new and more interesting answer with other implications for the podcasting industry.
“There are a few different ways that ChatGPT could be used by podcasters:
- As a co-host: ChatGPT could be used as a virtual co-host for a podcast, participating in the conversation and providing insights or commentary on the topic being discussed.
- As a guest: ChatGPT could be used as a virtual guest on a podcast, participating in the conversation and providing information or perspectives on a particular topic.
- As a content generator: Podcasters could use ChatGPT to generate ideas for episode topics or to generate script outlines for specific episodes.
- As a transcription service: ChatGPT could be used to automatically transcribe podcast episodes, allowing podcasters to create written transcripts of their episodes for their listeners.
- As a language translation service: ChatGPT could be used to automatically translate podcast episodes into other languages, allowing podcasters to reach a wider audience.”
I asked ChatGPT to expand on its potential use as a co-host. (Right now, there’s no way to upload audio for it to interpret. It is strictly a text-based tool, so a live-action co-hosting situation seems… complicated.)
It responded that it “does not have a physical body or a voice of its own. However, it is possible to use text-to-speech technology to generate a synthetic voice that can be used to ‘speak’ the responses generated by ChatGPT.”
These are exciting possibilities, some of which are already available in products on the market. For example, Descript, the podcast and video production tool that I rave about, uses AI to enhance audio automatically and has a feature called Overdub that allows you to create a voice model. So if I forget to say something in my recording — or I just want to correct a few words I said — I can type that message into Descript, and it will create that audio with my voice.
That’s pretty cool.
I can create other voice models as well, so long as my cohosts or subjects are willing to sit for 10 minutes to record a script that the voice model is built on.
Transcripts lead to new opportunities
Descript also provides an AI-generated transcription service (although their transcripts are pretty rough). Other players seem to understand the importance and power of transcripts, which leads to some interesting possibilities for how artificial intelligence tools will drive podcasting this year.
Deciphr.ai, a new tool I’m experimenting with, promises to take your audio or transcript and create a summary of your episode, give you timestamps for chapter markers, and will throw in highlights for you in case you want to go back and make some audiograms or video clips.
I asked Deciphr.ai to do its magic on an episode from Mistakes That Made Me, a podcast I produced for copywriting superstar Eman Ismail. True to its word, it had a summary for me within 60 seconds. Here are the first two paragraphs.
“Star Melancon is a financial strategist and CEO and founder of She Building Her. In this conversation, she discusses how not setting boundaries in her life and business had devastating consequences, but is also the reason she was able to become the financial expert she is today.
“Star Melancon shares how her company, She Building Her, came to be in a dream. She then discusses how the company helps women support and empower one another. Eman Ismail expresses her admiration for the company name and mission.”
It’s not the best copy, but that’s not the point. It’s a starting point for me or you to edit into something more compelling for our audience.
And most importantly, it saves time on repetitive and non-creative tasks.
Instantly generated marketing and promotional material
For me, this is the holy grail. I spend a lot of time working on the little things for clients, including show notes and video clips that accompany each podcast episode. So it’s helpful to have tools that can speed up that process. Many AI tools are built specifically for this.
I’ve mentioned Descript before and how it allows you to create stylish video clips and audiograms. There are other new AI tools (that are still working out their bugs) coming to market that promise a full-blown marketing kit for each audio file uploaded. Dubb.media is built in that mold. I gave it the same Mistakes That Made Me episode, and it spat back out titles, descriptions, keywords, video clips, a Twitter thread, audio clips, top quotes, a blog post, and a transcript.
I was impressed.
Now, there are lots of caveats to Dubb.media. But mostly, it’s not a consumer-ready product. There is limited control over the video (you have the options of artsy, blocky, or spooky), and the turnaround is 1 to 2 hours. But their copy was much better than I expected. And most importantly, it’s a preview of what’s to come — instantly generated text, audio, and video, with little-to-no creator input.
Summary: How artificial intelligence tools will drive podcasting in 2023
AI tools are here to help. These tools and others like them are what will drive the industry forward to make podcasting more inclusive and address exploding production and marketing costs. And these tools are maturing at a time in which the creator economy is converging, requiring the tools and systems we use to be able to handle the overlap being produced.
Not only do my clients want to produce great audio stories, but they also want to be well-represented on social media, have a dynamic presence on YouTube, and have specialized content for the most engaging online platforms — whether that’s TikTok or Instagram Reels.
It’s a lot.
That’s where AI tools will help the most. And in turn, the businesses and creators I represent will have more time to focus on their work or other creative pursuits. That’s what we all want.
That’s a wrap for this month. I hope something you see here helps your productivity and saves you time. But if you still have questions, I’m here to help. Let me know your thoughts, feedback, or podcast recommendations by leaving a comment below. If you want more content like this in your inbox, sign up for my monthly newsletter here.