generate high-quality, human-like speech with ~200ms latency, reducible to ~100ms.
zero-shot voice cloning and guided emotion control using tags.
canopylabs/orpheus-3b-0.1-ft · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
https://huggingface.co/canopylabs/orpheus-3b-0.1-ft

Seonglae Cho