It began as an experiment. I had no intention of becoming my own audiobook narrator. Not when there were perfectly capable AI voices like Martin and Mary vying for the honor. Martin, my first choice, had warmth but occasionally took creative liberties that made me question his sobriety. Mary, on the other hand, had perfect pacing and flawless pronunciation, but her delivery felt like a polite voicemail from a distant cousin.
At one point, Martin mispronounced “pince-nez” as “pans nes” and “agape” as “agahpay.” Another time, he insisted on saying “Khinayda” as “Canada,” and I nearly went Super Saiyan. Yet, despite his crimes against diction, there was something about Martin’s delivery that occasionally caught me off guard—a flicker of real emotion. I’d listen back and think, Huh. He actually felt that.
Mary had none of that. She was precise and consistent, like a metronome wearing pearls. I wanted to love her voice, but every time she read a line meant to bleed, it landed with the emotional heft of an Excel formula. After a long tug-of-war between the two, Martin eventually redeemed himself with better pronunciation, steadier pacing, and a delivery that managed to sound, at least occasionally, like a heartbeat. AI King status restored.
Still, even with all my tinkering, the limits were clear. Apple Books’ auto-narration had emotion but couldn’t fix mispronunciations (they do not allow editing or phonetic guidance). Google Play Books’ version got the words right but stripped the soul from them. One platform spoke clearly but without feeling; the other spoke feelingly but without clarity. And as a storyteller, I realized I couldn’t keep handing over my characters’ voices to software that didn’t understand their pain, humor, or history.
So I made the decision to take the mic myself.
Some people say they actually like the sound of my voice—poor souls, truly—but I decided to lean into it. If I can write the story, edit it, design the cover, and market it, then why not bring it to life the way it was meant to sound? I know every rise and fall in tone, every pause that carries grief, and every laugh that doesn’t need to be perfect, just honest.
In the end, that’s what this all comes down to—honesty. The kind that can’t be programmed or generated. The kind that comes from sitting alone in a room with a microphone and choosing to tell the story one more time, this time out loud. Technology can assist, but it can’t replace the human connection that happens when words are spoken from the heart. So I’ll keep working heartily, mic in hand, heart on sleeve, ready to give my stories the sound they deserve.
Because at the end of the day, Martin tried. Mary tried. But this time, it’s personal.
Now if you’ll excuse me, I have a microphone to assemble and a cat who’s already claimed my soundproofing blanket as her new throne.
