From Choir Rejection to AI-Driven Podcasting Triumph: Creating High-Quality Content Without Recording
Learn how to use face swaps, voice cloning, and lip-syncing to create high-quality content effortlessly - without recording.
Introduction
Hey there, fellow crime thriller aficionados and AI enthusiasts! Today, I want to dive into something that has revolutionized my approach to content creation: AI-driven podcasting and video production. You see, I've always been a bit hesitant to jump into the world of podcasting due to the setup and recording hassles. Plus, let's face it—my voice isn't exactly the most pleasant to listen to. However, recent advancements in AI have drastically changed the game, making it easier and more efficient to create high-quality content. And for me to do that without filming or recording anything! And with better quality output than I have ever achieved before, thanks to AI!
And while this technology can be used for good (as I present here), it can also be use for evil, creating deepfakes, and provides some ideas for upcoming story lines in my crime thriller writing! But, we’ll only use it for good, right? RIGHT!
Background
A little backstory: I've never had much luck with my voice. In ninth grade, I was one of the few who didn't make the choir, out of 104 students who auditioned! Fast forward to today, and while I no longer have a dedicated filming space like I did when I conducted online training courses, AI has stepped in to save the day. With tools that can do face swaps, voice cloning, and lip-syncing, creating content has never been more accessible or exciting. And it is higher quality than my previous efforts.
Over the past year, these AI tools have improved massively. I'm talking about using MY face instead of an avatar, cloning MY voice, and perfectly syncing my lips to the spoken words. The tools I experimented with last year have made leaps and bounds in their capabilities.
Step-by-Step Guide
Let's break down how you can harness this technology for your own content creation. First, the tools that I use include Synthesys, PlayHT, and Canva. I have an inexpensive lifetime subscription to Synthesys, and annual subscriptions to Canva and PlayHT, (both which I use for a lot of different purposes).
Step 1: Your Image
First, you need a good-quality image of yourself. It should be square, around 512 x 512 pixels, and in JPG or PNG format. Make sure your face is front-facing and your mouth is closed.
This will be the base for your AI-generated avatar, and I uploaded it in my case to Synthesys to use instead of the many avatars they provide. (I want this to look like ME!)
Step 2: Cloning Your Voice
Voice cloning technology has seen incredible advancements. While Eleven Labs is the industry leader, it’s quite expensive. I found Synthesys and PlayHT to be very cost-effective alternatives. Creating a clone of your voice is straightforward. Record about a minute of natural-sounding speech, clean up the audio using tools like Audacity, and upload it to the voice cloning software. This process might take a few tries to get perfect, but it’s well worth the effort. (I also want my audios to sound like ME!)
Step 3: Creating Your Lip-Syncing Avatar
For the lip-syncing part, Synthesys shines. Even though I prefer the voice quality from PlayHT, Synthesys offers excellent lip-syncing and face-swapping capabilities along with voice cloning. But I chose the extra step of doing my audios in PlayHT as I thought it was better and worth the few extra minutes it took to integrate that into the process with Synthesys.
Once you have your custom voice clone, in PlayHT, you can then ongoing create your audios in PlayHT, and upload your audio file to Synthesys, then select your face, and generate your talking head lip-syncing video.
Step 4: Putting It All Together
For final video creation, I use Canva because of its simplicity and integration with Synthesys. Canva allows me to add background scenes, text overlays, and other objects effortlessly.
By setting up templates in Canva, I can create compelling videos in 15-45 minutes, without the need for any video or audio recording or editing, saving me hours of work per video by using these AI tools.
Call to Action
So, why am I so excited about this? These tools eliminate the need for a dedicated filming space, perfect voice conditions, or extensive editing. You can create video book trailers, podcasts, online training courses, and social media videos, even if you’re lounging in your pajamas with a sore throat. The possibilities are endless, and the process is easy and cost-effective.
If you’re intrigued and want to see an example, check out this video where I review Anne Lamott’s Bird by Bird.
The video showcases how seamlessly the technology works, using my cloned voice and face. You can find my review of Bird by Bird on my author services website, InkIT Publishing, if you're interested in the full book review. (BTW, this video is not meant to be a finished product, and is only a portion of the book review, but enough to show you the concepts at work.)
Upcoming Blogs and Other Resources
In the coming weeks, I’ll be diving deeper into the specifics of each tool I’ve mentioned, and more tips and tutorials on how to create and optimize your own AI-generated content. Stay tuned for blogs on voice cloning with PlayHT, lip-syncing with Synthesys. And watch for my new podcast starting soon. I’m not sure what the precise focus for the podcast should be yet, so that comes first. And if you have any ideas on that, leave me a comment below.
I’d love to hear how you plan to use these AI tools in your own content creation journey. Let’s explore this exciting new frontier together!
Note: There are affiliate links within this blog post to products and services that I recommend and use personally. This means that I receive a small percentage of sales commission with no extra cost to you and in some cases, you may receive a discount for using my links. I only recommend products and services that I believe are great for authors and other creatives. For more information, you may check out our Affiliate Marketing Policy, which can be found on my author services website..