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 FaceWe’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