Chatterbox TTS Demo with Script Processing

Generate high-quality speech from text with reference audio styling and batch processing capabilities.

Text to synthesize (max chars 300)

Reference Audio File (Optional)

0:00

Exaggeration (Neutral = 0.5, extreme values can be unstable)

0.25 2

CFG/Pace

0.2 1

Output Audio

Script Input (section headers start with a digit, e.g., '1 Introduction', '2. Chapter Two')

Total Paragraphs: 0 | Total Words: 0

Sections: None

Audio files will be saved to: /home/user/app/generated_audio

Global Generation Settings

Reference Audio File

0:00

CFG/Pace

0 1

Set All Exaggeration Values

0.25 2

Generation Status

Crossfade Duration (seconds)

0 1

Pause Between Segments (seconds). Crossfade must be 0

0 2

Section Number

Merge Status

Merged Audio