A solo maker built an ebook-to-audiobook app with AI coding agents
An ebook-to-audiobook service was built to turn ebooks into long-form narration with realistic AI voices. -based voice tools felt too expensive for limited use, while the open Kokoro voice model sounded natural enough for hours of listening without the tired feeling caused by older robotic voices. Kokoro is designed to run fast, but generating long audio on a 12-core laptop CPU was still too slow.
A cloud GPU setup was chosen so audiobooks could be generated quickly for a self-hosted library and possibly offered as a product for others. The project had two goals: build a product focused on ebook conversion, and get real experience with coding workflows. Almost all of ebookaloud was written by DeepSeek v4 inside OpenCode.
Over one month, the build used about 750 million tokens and cost $12 in credits. Each feature or change followed a plan, implement, test, review, correct, and commit cycle, using a mix of Pro and Flash agents.
Key points
- The product turns ebooks into audiobook-style narration with realistic AI voices.
- Kokoro sounded good, but CPU generation on a laptop was not fast enough for long books.
- Cloud GPU processing was used to make audiobook generation faster.
- Almost all of the app was written by DeepSeek v4 inside OpenCode.
- The project used about 750 million tokens over a month and cost $12 in credits.