I got tired of expensive text-to-speech APIs, so I built my own

Hey devs 👋 Over the past few months, I’ve been experimenting with different text-to-speech (TTS) tools and APIs. And honestly… most of them left me frustrated. Here’s why: Pricing gets expensive really fast Character limits are restrictive Some voices still sound robotic Too many steps just to generate a simple audio So I decided to build my own. Not to compete with the big players — but to create something simple, fast, and actually usable. What I focused on Instead of adding too many features