SUZA Voice Studio is a powerful, elegant offline text-to-speech application based on the Piper TTS engine. Generate natural-sounding speech with 29+ English AI voices without requiring an internet connection. (The models will need a network connection to download automatically when you run first time, and then it works fully locally.)
- Completely Offline: No internet connection required, 100% privacy
- 29+ Neural Voices: High-quality AI voices in US and UK English
- Modern UI: Sleek, intuitive interface with a dark theme
- Free & Open Source: No usage limits, no API costs
Download the ready-to-use installer from our website:
🔗 Download SUZA Voice Studio Installer
The installer version:
- Comes pre-bundled with all dependencies
- Ready to launch and work right away.
To run SUZA Voice Studio from source:
-
Clone this repository
git clone https://github.com/Umair-Fareed/piper-windows-ui.git cd piper-windows-ui -
Install dependencies
pip install -r requirements.txt -
Run the application
python piper_ui.py
- Select a voice from the dropdown menu
- Type or paste your text
- Click "Generate" to create speech
- Play, save, or export the generated audio
Voice models are downloaded automatically the first time you use a voice.
This project is open source and available under the MIT License.
- Based on the Piper TTS engine
- Voices trained on open datasets
- Voice models are downloaded on-demand when first selected
- Generated audio files are saved in the output folder with names based on the text content
- Voice samples help you choose a voice before downloading the full model
This application uses the Piper TTS engine for speech synthesis. And is created by SUZA.