Audio · Released Oct 2026
Gradium Phonon
Gradium's 31M-parameter English text-to-speech model, run on device by Ollama on Apple silicon Macs. It reads text as written, so numbers and dates are best spelled out.
Phonon is an open-weight audio model built by Gradium. It generates audio from a text prompt. It runs entirely on your own hardware through Ollama: no API key and no per-use fees.
Supported OS
macOS
Minimum machine configuration
macOS on Apple silicon · 8 GB RAM · English speech
Download size · ~0.1 GB
Specs
- Released
- Oct 2026
- Pricing
- Free, runs on your hardware
About the creator
Gradium
Gradium builds voice AI models, including Phonon, a family of small text-to-speech models that run on device.
gradium.ai ↗