Bright Oddity Press
Audiobook Studio 2.0 docs

1.x → 2.0 at a Glance

Here's the short version of what changed from 1.x to 2.0: what you feel day to day, and what developers gain.

At a glance
  • Synthesis moved to a managed TTS Server.
  • A real orchestrator runs the queue and recovery.
  • Engines and voices are installable bundles.
  • A plugin SDK and external API open Studio up.

What's new

  • Plugin SDK and external TTS API. Wrap engines and drive Studio from your own tools. See Plugin SDK and TTS Gateway API.
  • Composite synthesis across engines in one chapter.
  • Project backups and disk-based recovery.
  • Predictive progress with ETAs, and VCR-style playback in the editor.
  • Voice icons and tags, making a real, searchable library. See Voice Icons & Tags.
  • Clearer first-run model-download progress.
Coming soon: installable engines from GitHub, the Hugging Face voice library, and AI voice casting.

What users feel day-to-day

More reliability and less lost work. Crashes are contained, progress is steadier, and restarts recover. Voices get icons and tags; playback and the editor are smoother.

What developers gain

Clean extension points. A five-method plugin SDK, installable engines from GitHub, shareable voices on Hugging Face, and a documented gateway API. See this section's other pages for detail.