Audiobook Studio 2.0 docsWhat Is Audiobook Studio
Audiobook Studio is a local-first app that turns a manuscript into a finished, multi-voice audiobook using AI voice cloning, all on your own machine.
- It runs on your computer; your text and audio stay local unless you choose otherwise.
- It's a production tool, not one-click text-to-speech: you direct the narration line by line.
- One default local engine means no accounts and no per-word cost.
- You assemble narrated chapters into a real audiobook file (M4B/MP3).
A production tool, not a "read it aloud" button
Most text-to-speech tools give you one voice and one pass. Audiobook Studio is built for the messy reality of a whole book: many characters, lines that need a second take, pronunciation you want to fix, and a finished file at the end.
You stay in control of the result. Assign a voice to the narrator and a different one to each character, regenerate just the lines you change, and listen back as you go.
Local-first by design
Everything stays on your computer unless you choose a cloud engine. See Local-First & Privacy.
How the pieces fit together
- Project & chapters: your book, broken into chapters of text.
- Voices & casting: voices assigned to the narrator and characters.
- Generation: a managed engine turns assigned text into audio.
- Assembly: finished chapters become a single audiobook file.
In 2.0, generation runs in a managed, crash-isolated TTS Server with installable engines. See Studio 2.0 at a Glance.