Local audiobook pipeline

Queue an ebook at night, wake up to an audiobook: a proper .m4b with chapters from the book's table of contents, embedded cover art, and a voice matched to the material, synthesized entirely on my own hardware. None of my reading touches a cloud service.

Why not a cloud voice

Most read-aloud features are a thin wrapper around a big-tech cloud voice, and the ones that aren't tend to sound like a fax machine. I wanted listenable neural narration for my own library without shipping the library to anyone.

Replacing the scraper

The first version of the converter didn't synthesize anything itself; it drove a free TTS website through a scripted browser session. CAPTCHAs, session expiries, and layout changes kept killing overnight runs halfway through a book. The fix was to stop borrowing someone else's infrastructure. I stood up Kokoro, a neural TTS model with an OpenAI-compatible API, on my home server running entirely on CPU, and rewrote the converter's backend against it. No CAPTCHAs, no cloud, and the whole pipeline became boringly reliable.

Around the converter sits the automation that makes it a pipeline and not just a script: a queue directory watched by a systemd timer, a render worker on the server, and an idempotent import step that files finished books into Audiobookshelf, where they sync to my devices.