zyphra

Zonos v0.1 Transformer is a text-to-speech model from Zyphra built on a pure transformer architecture. It offers the same American and British English voice coverage as the Hybrid variant, and is suited for deployments where a transformer-only inference stack is preferred.

Zonos v0.1 Hybrid is a text-to-speech model from Zyphra built on a hybrid architecture. It produces English speech output with coverage across American and British accents in male and female voices. It is suited for English-language voice applications requiring accent and gender variety.