Canopy Labs Orpheus v1 English

Canopy Labs Orpheus v1 English is an open-weight text-to-speech model that generates highly natural, expressive English speech. It uses a transformer-based architecture to produce audio with realistic prosody, emotion, and speaking style, going beyond the flat, robotic output typical of earlier TTS systems.

The model supports multiple voices and speaking styles, with the ability to convey emotional nuance such as excitement, hesitation, and emphasis. It can also perform zero-shot voice cloning from a short audio reference sample.

Orpheus v1 English is designed for content creation, audiobook production, conversational AI, and accessibility applications, offering an open alternative to proprietary TTS APIs.