Settings

Configure audio devices, models, and application preferences

Audio

Input Device

Output Device

Sample Rate

Buffer Size

Models

TTS Model

Qwen3-TTS-0.6B

Loaded

STT Model

Whisper Large-v3

Loaded

Preload on Start

Load models when the application starts

Watermarking

Enable Watermarking

Watermark all generated audio for authenticity verification

Storage

Voice Profiles

12 voices saved

Audio Cache

1.2 GB used

Export Location

~/Desktop

About

Version

1.0.0

Hardware

Apple Silicon M2 Pro (MPS enabled)