Installation
Download and install Sonna on macOS, Windows, or Linux
Download
Sonna is available for macOS and Windows, with Linux builds coming soon.
macOS
Download for Apple Silicon or Intel Macs
Windows
Download MSI installer or Setup executable
macOS
Download: sonna_aarch64.app.tar.gz
# Extract the archive
tar -xzf sonna_aarch64.app.tar.gz
# Move to Applications
mv Sonna.app /Applications/Download: sonna_x64.app.tar.gz
# Extract the archive
tar -xzf sonna_x64.app.tar.gz
# Move to Applications
mv Sonna.app /Applications/Windows
Download: sonna_x64_en-US.msi
Double-click the MSI file and follow the installation wizard.
Download: sonna_x64-setup.exe
Run the executable and follow the installation wizard.
Linux
Linux builds are coming soon. Currently blocked by GitHub runner disk space limitations.
First Launch
When you launch Sonna for the first time:
-
Model Download — The TTS engine you generate with first will download its model automatically. Sizes range from ~350 MB (Kokoro) to ~8 GB (TADA 3B). Most users start with Qwen 1.7B (~3.5 GB).
-
Data Directory — Voice profiles and generated audio are stored in:
- macOS:
~/Library/Application Support/sh.sonna.app/ - Windows:
%APPDATA%/sh.sonna.app/ - Linux:
~/.config/sh.sonna.app/
- macOS:
-
Backend Server — The bundled Python server starts automatically
First generation will be slower due to model downloads. Subsequent runs use cached models.
System Requirements
Minimum
- OS: macOS 11+, Windows 10+, or Linux
- RAM: 8GB
- Storage: 5GB free space (for models and data)
- CPU: Modern multi-core processor
Recommended
- RAM: 16GB+
- GPU: CUDA-capable NVIDIA GPU (for faster generation)
- Storage: 10GB+ free space
CPU inference is supported but significantly slower than GPU. A CUDA-capable GPU is highly recommended for real-time workflows.
Verification
After installation, verify everything works:
- Launch Sonna
- Check the server status indicator in the bottom-left corner (should be green)
- Navigate to Profiles and create a test profile
- Generate a short audio clip to verify the TTS engine works
If you see a green status indicator and can generate audio, you're all set!
Next Steps
Quick Start Guide
Create your first voice profile and generate speech