canopyai/Orpheus-TTS
A state-of-the-art open-source text-to-speech system leveraging LLMs to generate human-like, emotional, and low-latency speech with zero-shot voice cloning capabilities.
Core Features
Quick Start
git clone https://github.com/canopyai/Orpheus-TTS.git && cd Orpheus-TTS && pip install orpheus-speechDetailed Introduction
Orpheus TTS is a cutting-edge open-source text-to-speech system built on the Llama-3b large language model backbone, showcasing the emerging potential of LLMs in speech synthesis. It excels at producing highly natural, emotional, and rhythmic human-like speech, often surpassing commercial closed-source alternatives. Key capabilities include zero-shot voice cloning, fine-grained control over emotion and intonation, and ultra-low latency suitable for real-time applications. The project offers both English and multilingual models, along with tools for custom fine-tuning, making advanced speech generation accessible to developers and researchers.