Bright Oddity Press
Audiobook Studio 2.0 docs

Engines Overview

Studio can route synthesis to more than one engine. They split into local and cloud, with one local engine installed by default.

At a glance
  • Local engines run on your machine. XTTS is the only default install.
  • Cloud engines are optional and need an API key (e.g. Voxtral).
  • Composite synthesis mixes engines within a chapter.
  • More engines can be added as plugins.

Local engines

The default engine is local and private. XTTS is the one engine installed out of the box; it runs on your machine with no account. See Local Engine (XTTS Default).

Cloud engines

Cloud engines are optional and opt-in. You enable one with an API key; none ship by default. Voxtral is one example. See Cloud Engines.

Composite synthesis

A chapter can mix engines. Composite synthesis stitches output from multiple engines/voices into one chapter. See Composite Synthesis.

Plugins add more

Engines are installable. Beyond the default, you can add engines as plugins from GitHub. See the Plugin SDK.