CosyVoice

开源

多语种大型语音生成模式,提供推论,培训和部署全高架能力.

22.5K stars0 点赞0 次浏览

工具介绍

多语种大型语音生成模式,提供推论,培训和部署全高架能力.

👉🏻 CosyVoice 👈🏻 Fun-CosyVoice 3.0: Demos; Paper; Modelscope; Huggingface; CV3-Eval CosyVoice 2.0: Demos; Paper; Modelscope; HuggingFace Hun-CosyVoice 3.0是一款基于大语言模型(ZZTTERM0ZZ)的高级文本对发音系统,在内容一致性,扬声器相似性和亲相自然性上超过了它的前身(CosyVoice 2.0. 其被设计为野外零发多语言语音合成. 主要特色 - 语言覆盖:涵盖9种通用语言(中文,英文,日文,韩文,德文,西班牙文,法文,意大利文,俄文),18+ 中国方言/方言(广东,明南,四川,东北,山西,山西,上海,天津,山东,宁夏,甘肃等地)同时支持多语种/跨语种零镜头语音克隆. - 内容一致性和自然性:实现状态-o

核心特点

•Content Consistency & Naturalness: Achieves state-of-the-art performance in content consistency, speaker similarity, and prosody naturalness.
•Pronunciation Inpainting: Supports pronunciation inpainting of Chinese Pinyin and English CMU phonemes, providing more controllability and thus suitable for production use.
•Text Normalization: Supports reading of numbers, special symbols and various text formats without a traditional frontend module.
•Bi-Streaming: Support both text-in streaming and audio-out streaming, and achieves latency as low as 150ms while maintaining high-quality audio output.
•Instruct Support: Supports various instructions such as languages, dialects, emotions, speed, volume, etc.
•[x] 2025/12
•[x] release Fun-CosyVoice3-0.5B-2512 base model, rl model and its training/inference script
•[x] release Fun-CosyVoice3-0.5B modelscope gradio space
•[x] 2025/08
•[x] Thanks to the contribution from NVIDIA Yuekai Zhang, add triton trtllm runtime support and cosyvoice2 grpo training support