Studio
Docs

Project Editor

The main workspace for editing chapters, segments, and annotations.

Screenshot: Full project editor showing three-pane layout

Three-Pane Layout

The project editor has three main areas:

  • Left sidebar — Chapter list and navigation, plus Voices and Generate tabs.
  • Center pane — The segment editor for the selected chapter.
  • Right sidebar — Context-sensitive panels (segment details, annotations).

Chapters

Screenshot: Chapter list in the left sidebar

The chapter list shows all chapters in your project. Click a chapter to select it and view its segments in the center pane. Chapters can be expanded or collapsed.

  • Word count — Displayed on each chapter card.
  • Generation progress — Shows how many snippets are generated.
  • Play (▶) — Quick play for chapter audio directly from the list.
  • Add chapter (📕+) — Add a new chapter to the project.
  • Delete chapter (🗑) — Remove a chapter and all its segments.

Segments

Screenshot: Segment editor showing segments with role badges

Each chapter is divided into segments — blocks of text that map to individual audio snippets. Segments are displayed as cards in the center pane.

Role Badges

Each segment has a role badge indicating who speaks it:

  • Narrator — Default role for narration and description text.
  • Character name — Dialogue assigned to a specific character.

Editing Segments

Click on a segment to select it. Click the edit button (✏) to enter editing mode, where you can modify the text directly. You can also change the character assignment using the role dropdown.

Splitting a Segment

Sometimes a segment contains text that should be spoken by different characters, or you want finer control over a long passage. You can split a segment into two at any point:

1

Enter editing mode

Click on the segment to select it, then click the edit button (✏) to start editing.
2

Place your cursor

Click within the text at the exact point where you want to split. There must be text on both sides of the cursor.
3

Click "Split here"

Click the Split here button (✂) that appears in the editing toolbar. The segment will be divided into two new segments at the cursor position.
After splitting, you can assign each new segment to a different character using the role dropdown. This is especially useful when narration and dialogue are mixed in a single segment.

Drag-and-Drop Reordering

Segments can be reordered by dragging and dropping. Grab the drag handle (⠿) on the left side of a segment card and move it to a new position.

Segment Dividers & Glue

Between segments, dividers control how audio is joined. The glue toggle (🔗) removes the gap between two segments, making them flow together seamlessly in the exported audio. When unlinked (🔗̸), the normal inter-segment silence is used.

Annotations

Screenshot: Text with annotation markers and toolbar

Annotations let you control how text is spoken — adding emotion, vocal effects, or pacing changes to specific words or phrases. Each annotation appears as a colored badge on the annotated text.

How to Annotate

1

Select a segment

Click on the segment you want to annotate. It must not be in editing mode — if you're currently editing the text, press Escape or click outside first.
2

Highlight text

Click and drag to select the word or phrase you want to annotate. The annotation toolbar will appear below the segment.
3

Choose an annotation type

Click one of the annotation buttons in the toolbar. The selected text will be marked with a colored badge indicating the annotation type.

To remove an annotation, click the badge on the annotated text. You can apply multiple annotations to different parts of the same segment.

Annotations affect how the TTS engine generates audio. After adding or removing annotations, the segment will be marked as stale (if it was already generated) and you'll need to re-generate it to hear the changes.

Available Annotations

Emotions & Expressions

Add emotional delivery to dialogue and narration:

  • Angry — Aggressive, heated tone.
  • Sad — Melancholic, downcast delivery.
  • Scared — Fearful, trembling voice.
  • Excited — High-energy, enthusiastic tone.
  • Nervous — Anxious, uneasy delivery.
  • Cheerfully — Bright, upbeat tone.
  • Sarcastically — Dry, ironic delivery.
  • Bored — Flat, disinterested tone.
  • Confused — Uncertain, questioning delivery.

Vocal Effects

Add specific vocal sounds and reactions:

  • Whisper — Soft, hushed voice.
  • Shouting — Loud, projected voice.
  • Screaming — Intense, high-volume cry.
  • Giggle — Light, brief laugh.
  • Laugh — Full laugh.
  • Sigh — Audible exhale.
  • Gasp — Sharp intake of breath.
  • Crying — Tearful, choked voice.
  • Sobbing — Heavy, convulsive crying.
  • Whimpering — Soft, suppressed crying.

Pacing & Emphasis

Control the speed and weight of delivery:

  • Emphasis — Adds stress and weight to the selected words.
  • Slow — Reduces speech speed for dramatic effect.
  • Fast — Increases speech speed.
  • Pause — Inserts a beat after the selected text.

Reload & Reset

Reload File re-reads the original manuscript and recreates chapters and segments. Reset All clears all generated audio and resets the project to its initial state. Both actions require confirmation and cannot be undone.