Audiobook Studio 2.0 docsComposite Synthesis
Composite synthesis lets one chapter use more than one engine or voice, stitched into a single, seamless result.
At a glance
- Mix engines/voices within one chapter.
- Studio stitches the output together.
- Formerly called “mixed” synthesis.
When chapters mix engines
Sometimes the best cast spans engines. A narrator on the local engine and a specific character on another, for instance. Composite synthesis handles that within a single chapter.
How composite rendering stitches output
Each segment is rendered by its assigned engine/voice, then combined in order. Because completion is tracked per validated artifact, segments from different engines assemble cleanly into one chapter.
Note: Composite was previously called “mixed” synthesis; you may still see that term in older material.