canopyai/Orpheus-TTS
Orpheus TTS is a state-of-the-art open-source text-to-speech system built on a Llama-3b backbone, aiming to generate human-sounding, emotionally rich speech with low latency.
Core Features
Quick Start
git clone https://github.com/canopyai/Orpheus-TTS.git && cd Orpheus-TTS && pip install orpheus-speechDetailed Introduction
Orpheus TTS leverages the emergent capabilities of large language models (LLMs) for advanced speech synthesis, utilizing a Llama-3b backbone to achieve human-like speech quality. It excels in natural intonation, emotion, and rhythm, often surpassing closed-source alternatives. Key features include zero-shot voice cloning, guided emotion control, and low-latency streaming, making it suitable for real-time applications. The project offers both finetuned and pretrained English models, alongside a research preview of multilingual models, providing tools and data for custom fine-tuning.