The AI Daily Brief: Artificial Intelligence News and Analysis - The AI Stack for Content Creators (aka the AI Tools I Actually Use)

Episode Date: November 6, 2023

The best AI tools for content creators -- or at least the ones I use regularly, including Descript, HeyGen, Perplexity, ChatGPT, ElevenLabs, Canva Magic Studio and more.  ABOUT THE AI BREAKDOWN The A...I Breakdown helps you understand the most important news and discussions in AI.  Subscribe to The AI Breakdown newsletter: https://theaibreakdown.beehiiv.com/subscribe Subscribe to The AI Breakdown on YouTube: https://www.youtube.com/@TheAIBreakdown Join the community: bit.ly/aibreakdown Learn more: http://breakdown.network/

Transcript
Discussion (0)
Starting point is 00:00:00 Today on the AI Breakdown, we're looking at a content creators AI stack. In other words, the AI tools that independent content creators can use to improve the speed and efficiency of their work. The AI breakdown is a daily podcast and video about the most important news and discussions in AI. Go to Breakdown.network for more information about our YouTube channel, our Discord, and our newsletter. Welcome back to the AI breakdown. A couple of months ago, I did an episode called The AI Tools I Actually Use or something like that. and people really responded. Now, I had wanted to do that because at the time, one of the big categories of content and places like Twitter and Facebook was people saying, using chatypt is just
Starting point is 00:00:43 scratching the surface. Here are 18,000 tools that you need to know. I think that it served mostly to get people to feel overwhelmed and disempowered rather than what it was actually going for, which is to make people feel like there was a tool for absolutely everything that they could imagine. So, the goal of this video is not in any way to suggest that this is a comprehensive comprehensive list of all the tools that content creators can use, but is just a set of tools that I find myself using in a relatively frequent manner, so maybe this will inspire something for your own content creation and help you get your own AI content creation stack up and running. Let's start in the realm of research. Now, of course, basically any LLM, especially ones who are
Starting point is 00:01:22 connected to the internet, are going to help you with research, but I wanted to pay specific attention to perplexity. Perplexity is increasingly the research tool of choice for people who I know who are familiar with lots of the different AI options, and there are a few reasons for that. Let's take a look at the example that I'm using throughout this video by asking Perplexity, what is OpenAI announcing at Dev Day on November 6th? A few things about Perplexity that are worth noting. First of all, right up front, it shows you the sources that it draws from, and that happens before it gives you its answer. Now, this was sort of a hard question, because I didn't just ask for a description of what Dev Day was, but asked what they were actually announcing, the trick of which,
Starting point is 00:01:58 of course is that they haven't said what they're announcing. Perplexity comes back. OpenA.I is hosting its first ever developer conference OpenAI Dev Day on November 6, 2023 in San Francisco. While the specifics of the announcement are not detailed, OpenAI has indicated that they will be previewing new tools at the event. However, it has been confirmed that the announcement of GPT5, the presumed name of OpenAI's next flagship generative AI model, is unlikely, as OpenAI CEO Sam Altman confirmed in April that OpenAI wasn't training GPT5 and wouldn't for some time. Now, from there it begins to speculate about what might be revealed. Quote, there might be updates on OpenAI's plans for Global Illumination,
Starting point is 00:02:33 an AI design studio that it acquired in August, and an update on the availability of GPT4's image understanding capabilities. There are also reports that OpenAI plans to unveil new, possibly cheaper vision-capable developer tools at the conference. Now, for those of you who are listening rather than watching to this, one of the things of note is that after almost every sentence, certainly after every section, there are little footnotes which show you which source different information came
Starting point is 00:02:55 from. So even if it was just footnotes and summarization, it would already be a really useful research tool. But one of the other things that makes perplexity really cool is the way in which it prompts further or related questions. For example, it gives me the option to click, what are the new tools that OpenAI is planning to announce at Dev Day? How can developers register for in-person attendance at OpenAI Dev Day? What is the agenda for OpenAI Dev Day? Let's try the agenda. Now, in this case, it actually came back and asked me for further information. Let's do its suggestion keynote topics. Now, the answer here is pretty vague because it Again, this information hasn't really been premiered, but you can see how this related question
Starting point is 00:03:29 type of feature is really good for getting further information and for digging into a topic quickly. Let's move on now to another use for AI in the content creation process, which is scripting. Now, it should be noted that when it comes to these videos and these podcasts that you're hearing on the AI breakdown, I am completely unscripted. Every day I figure out what I want to talk about, I pull up the web windows, and I just let it rip. But of course, that's not the way that most people create videos and podcasts, and one of the things that these new LLMs are really good at is writing, which of course, with a little help,
Starting point is 00:03:59 can turn into scripting. So we selected the web browsing model of GPT4, and first I asked, what do you know about the OpenAI Dev Day happening on November 6th? It gave a little bit of information, which for me was really just about making sure that it knew what the context was for the thing that I was about to ask it next. I said, could you please write an intro script of 15 to 20 seconds for a video all about the event? Now, this actually was quite the fail. Its first suggestion began, welcome to OpenAI Dev Day, 2023. Unfolding this November 6th in the heart of San Francisco, this inaugural event ushers in anew. Now, at that point, I knew that it was thinking that I kind of wanted a hypey video or that I wasn't thinking journalistically, and just to confirm that I clicked
Starting point is 00:04:37 to regenerate and still had something similar. Get ready to step into the future of artificial intelligence at OpenAI Dev Day 2023. As you can see, this type of scripting was almost more like a promotional video than it was like what I was looking for, which was the intro to a video that was more journalistic in nature or more news analysis. So I stopped it and added this clarification. I'm a podcaster who covers news about the AI space. I'm doing a video about OpenAI's Dev Day. Can you please write a script for a 15 to 20 second intro about the event that focuses on what's interesting about it or the questions people are wondering about it? Please don't seem like you're shilling the event or hyping it up too much. This one, it did much better. Chat ChaptiPt responds,
Starting point is 00:05:14 absolutely, here's a balanced intro script for your video. OpenAI's inaugural Dev Day on November 6th unveils the space for global developers to converge and cross-pollinate ideas. As attendees get a first glimpse of new tools, the AI community is abuzz with questions. What innovations will be revealed? How will OpenAI's latest strides shape the development landscape? Join us as we delve into the unfolding narrative of OpenAI's Debday, 2023. Okay, so we are going to use that script for a couple other demonstrations throughout this video. The first of those is speech synthesis.
Starting point is 00:05:44 If you are a regular AI breakdown listener, you will know that the time that I use speech synthesis most often, is when I'm doing one of the long reads episodes where there's some big 10 or 15 or 20 minute piece, I will often have AI me read it instead of myself. But let's do a quick listen to hear how 11 Labs synthesizes my voice, which I've trained specifically for 11 Labs, doing that intro that ChatchipT just wrote. OpenAI's inaugural Dev Day on November 6th unveils a space for global developers to converge and cross-pollinate ideas. As attendees get a first glimpse of new tools, the AI community is a buzz with questions. What innovations will be revealed?
Starting point is 00:06:19 How will OpenAI's latest strides shape the development landscape? Join us as we delve into the unfolding narrative of OpenAI's Dev Day 2023. Now, as you can tell, it has perhaps a little bit less of the Vim and Vigor that I might if I was doing the intro to one of my own videos, but it's certainly not wooden and it's certainly not dead, and it certainly sounds a lot like me. Now, I did want to throw out that there is another tool in the same category that's actually kind of a more comprehensive tool. The editor that I use for all my videos and podcasts is Descript.
Starting point is 00:06:51 Descript allows you to edit videos by selecting text, and it has a number of different AI features, including the ability to automatically cut out all the filler words like ums and Oz. It has an overdub feature where you can actually type in words and have it speak in your voice in the right intonation so you can fix things in post-production. And it also now has AI-assisted writing that you can then have a voice that you've trained, read as a script as well. So just for giggles, even though it doesn't necessarily have the context,
Starting point is 00:07:15 and I'm not sure if it's wired to the internet, I asked it to please write a 50-word script introducing a video about OpenAI's Dev Day developer event on November 6th. Let's see what it comes back with. It writes, Welcome to OpenAI's Deb Day, the must-attend developer event happening on November 6th. Join us for a day of deep dives, technical talks, and interactive sessions with experts. Discover the latest advancements in AI research, explore cutting-edge technologies, and connect with a vibrant community of developers from around the world. Now, obviously this is doing the promotional video thing, but just because I'm doing it as a
Starting point is 00:07:43 demonstration, let's add it to the script, and then click Add a Sucing. speaker and see how it sounds. Welcome to OpenEyes Dev Day, the must-attend developer event happening on November 6th. Join us for a day of deep dives, technical talks, and interactive sessions with experts. Discover the latest advancements in AI research, explore cutting-edge technologies, and connect with a vibrant community of developers from around the world. Don't miss out on this exciting opportunity to learn, network, and shape the future of AI. Save the date and mark your calendars for OpenEy's Dev Day on November 6th. So the way I would describe this
Starting point is 00:08:21 is that it would be very impressive if it was about six to nine months ago. But now, obviously, it doesn't really hold a candle to 11 labs, although there are options that I haven't taken to further train and fine tune a voice model in Descript, so it could be more my action than the script itself. However, when it comes to the use for patching videos,
Starting point is 00:08:39 it's an unbelievably powerful integration that makes editing a totally different type of experience. But what if I don't just want audio, what if I actually want video, and for whatever reason, I don't have the time to get on camera. Well, as Hey Jen's landing page puts it, no camera, no crew, no problem. So this is what Hey Jen looks like inside. I've trained one of these instant avatars on myself and then fine-tuned it. And so let's get a preview of what it looks like before we see the video with this specific script applied.
Starting point is 00:09:06 Hey, Nathaniel Widimore, your instant avatar is ready. Feel free to create videos with it. Also, click the feedback button to share what you think. Hope you enjoy. Now, one of the big reflections that I had upon seeing this Instant Avatar video is that I probably bounce around too much when I'm filming, because the AI has clearly picked up and mimic that action in a way that I find fairly distracting, but frankly, that is a notch in the AI's favor, as it actually picked up on a distinct tick that I have when I shoot my videos.
Starting point is 00:09:31 Now, when it comes to creating a video that has this specific script, you click create new video, you add speech, or I've copy-pasted the chat GPT script, and then I've selected the avatar. I'm going to press submit, and then we wait for it to be ready. OpenAI's inaugural Dev Day on November 6th unveils a space for global developers to converge and cross-pollinate ideas. As attendees get a first glimpse of new tools, the AI community is a buzz with questions. What innovations will be revealed? How will OpenAI's latest strides shape the development landscape?
Starting point is 00:10:06 Join us as we delve into the unfolding narrative of OpenAI's Dev Day 2023. So as you can see from that video, this is far as. from perfect. There's a lot to be said for just getting on camera and actually doing it yourself. But man, just the availability of something like this with an avatar that you can train on yourself opens up so many new possibilities in terms of the speed of content creation, the precision, and frankly the cost. Although yes, there is a cost to using Hey Jen. It's nothing compared to the time that an editor takes. Okay, so we've got our video now. Let's make some key art such as for a YouTube thumbnail. For any given image that I'm working on, there are two services
Starting point is 00:10:44 that I use most often. Those are Dolly 3 and Mid Journey. Now, Mid Journey for a very long time was my go-to. The new capacity that Dolly 3 adds is the ability to actually have words inserted, which can make a huge difference. You can see here that I've asked, please make a YouTube thumbnail 16 by 9 for a video about OpenAI's Dev Day developer event on November 6th in San Francisco. It created two, one that has a Golden Gate Bridge theme, and another that has a sort of cool computery illustration view of San Francisco with some generic tech accents to make it feel modern. Now, these are fine, but if I wanted something perhaps a little bit more artistic, mid-jurney might be a better call. The prompt I used for this was poster image for an
Starting point is 00:11:22 artificial intelligence event for developers in San Francisco. Now, these aren't perfect enough I was doing this for real. I would certainly be refining them and experimenting with different prompts to try to get a little bit more of what I wanted, but stylistically, number two is close enough to be going on, and so I wanted to bring it to the last tool that I use very regularly, which is Canva. Now, Canva has tons of non-AI features. It's just a good place to layout images, be they thumbnails or something else. But they also have a whole new set of AI tools, one of which is called Magic Switch. Part of Magic Switch is a Magic Resize. So for example, I could turn this into a square thumbnail just with a single click. Let's do that and see what comes
Starting point is 00:11:57 back. We click Copy and Resize, then open it up. Boom, sure enough, it's there. Now, of course, with something this simple, it wouldn't have been all that hard to just do this manually. But sometimes the point of these AI tools isn't to be totally revolutionary. It's to save seconds or minutes that you could use for other purposes. But now let's try a different capacity of Magic Switch, which is translate. Let's translate it to Spanish. This sort of linguistic translation is something that I think is going to be hugely significant, and in fact gets to the last category, which is a tool set that I haven't integrated yet, but which seems like it's inevitably just around the corner. That is the crazy world of AI-powered dubbing. Now, a lot of the big platforms have started to announce
Starting point is 00:12:36 dubbing features, including YouTube and Spotify, but a number of startups like Wondercraft are also offering this as well. My strong instinct is that within a year or two, the default will be for a lot of the content that we create to be automatically translated into at least another half dozen languages or so, which if that actually happens, will break down global linguistic barriers in a huge, huge way. And so, friends, that is where we will wrap. Like I said, this is far from a comprehensive list of AI tools for content creators, but it is one content creator's AI stack. I hope, of course, that you found this useful and that it inspired some ideas for you to go off and use on your own. I appreciate you listening or watching as always, and until next time, peace.

There aren't comments yet for this episode. Click on any sentence in the transcript to leave a comment.