Chatterbox TTS Server

Generate Speech

Text to synthesize

Enter the text you want to convert to speech. Standard punctuation will be recognized.

0 / 8192

Split text into chunks

Voice Mode:

Predefined Voices Voice Cloning (Reference)

Select Predefined Voice:

Load Example Preset:

Loading presets...

Generation Parameters

Temperature (0.8)

Exaggeration (0.5)

CFG Weight (0.5)

Speed Factor (1.0)

Generation Seed

Integer for reproducible results. Some engines use 0 or -1 for random.

Server Configuration

These settings are loaded from config.yaml via an API call. Restart the server to apply changes to Host, Port, Model, or Path settings if modified here or directly in the file.

Server Host

Server Port

TTS Device

Default Voice ID

Model Cache Path

Predefined Voices Path

Reference Audio Path

Output Path

Audio Output Format

Audio Sample Rate

Resets settings to their defaults.

Tips & Tricks

Use **Predefined Voices** for consistent, high-quality output. You can import new ones.
For **Voice Cloning**, upload clean reference audio (.wav/.mp3). Quality of reference is key.
Experiment with **Temperature** and other generation parameters to fine-tune output.
Enable **Split text** for very long inputs. Max chunk size is now 1000 characters.
Adjusting **Speed Factor** away from 1.0 is experimental and may cause echo.
Check the /docs endpoint for API details.

Generate Speech

Tips & Tricks

Chunking Voice Consistency Warning

Generation Quality Notice