Voice Assignment
Assign voices to speakers, characters, and sections in your project for multi-narrator audiobooks and scripted content.
Voice assignment lets you map different voices to different parts of your project. Use any combination of built-in voices, cloned voices, and designed voices from the Lab.
Assigning Voices
Each section in your project has a default voice. To assign a voice, select a section and pick from your available voices:
- Built-in voices from the TTS tab
- Cloned voices from the Clone tab
- Designed voices from the Design tab
- Community voices imported from Voice Search
Mix and match freely. For example, use a cloned narrator voice for prose and designed character voices for dialogue.
Per-Segment Overrides
You can override the section-level voice for any individual segment. Select the segment and choose a different voice from the voice dropdown. This is useful when a section has occasional dialogue from a different character.
Inline Voice Spans
For the most granular control, highlight a span of text within a segment and assign a different voice to just that selection. This lets you handle cases like:
- Quoted dialogue embedded in narration
- A character interrupting the narrator
- Multiple speakers within a single paragraph
The surrounding text keeps the segment's default voice while the highlighted span uses the override voice.
Workflow Tips
- Save voices to your library in the Lab before starting a project so they are ready to assign
- Preview before bulk generation. Generate a few key segments first to make sure each voice sounds right in context before generating the full project