CosyVoice 是一种语音克隆模型。以下是关于 CosyVoice 的相关信息：
[[Paper](https://fun-audio-llm.github.io/pdf/FunAudioLLM.pdf)][[Code](https://github.com/FunAudioLLM)][Modelscope:[SenseVoice](https://www.modelscope.cn/studios/iic/SenseVoice)[CosyVoice](https://www.modelscope.cn/studios/iic/CosyVoice-300M)][HuggingFace:[SenseVoice](https://huggingface.co/FunAudioLLM/SenseVoiceSmall)CosyVoice]Tongyi SpeechTeamAlibaba GroupAbstract:This report introduces FunAudioLLM,a framework designed to enhance natural voice interactions between humans and large language models(LLMs).At its core are two innovative models:SenseVoice for high-precision multilingual speech recognition,emotion recognition,and audio event detection;and CosyVoice for natural speech generation with multi-language,timbre,and emotion control.SenseVoice delivers exceptionally low latency and supports over 50 languages,while CosyVoice excels in multi-lingual voice generation,zero-shot voice generation,cross-lingual voice cloning,and instruction-following capabilities.The models related to SenseVoice and CosyVoice have been open-sourced on Modelscope and Huggingface,along with the corresponding training,inference,and fine-tuning codes released on GitHub.By integrating these models with LLMs,FunAudioLLM enables applications such as speech translation,emotional voice chat,interactive podcasts,and expressive audiobook narration,thereby pushing the boundaries of voice interaction technology.Contents
?Xiaohu.AI日报「12月29日」✨✨✨✨✨✨✨✨1⃣️?️数字人工具推荐：开源且适合小白用户特点：一键安装包，无需配置环境，简单易用。功能：生成数字人视频，支持语音合成和声音克隆，操作界面中英文可选。系统兼容：支持Windows、Linux、macOS。模型支持：MuseTalk（文本到语音）、CosyVoice（语音克隆）。使用步骤：下载8G+3G语音模型包，启动模型即可。?GitHub：[https://github.com/modstart-lib/aigcpanel](https://github.com/modstart-lib/aigcpanel)?官网：[https://aigcpanel.com](https://aigcpanel.com)?[https://x.com/imxiaohu/status/1872852432549765195](https://x.com/imxiaohu/status/1872852432549765195)2⃣️?Google Veo 2：AI生成逼真的Vlog视频效果：生成的视频接近真实，几乎难以分辨。应用：适合创作和内容制作。?[https://x.com/imxiaohu/status/1872984285634019476](https://x.com/imxiaohu/status/1872984285634019476)
?Xiaohu.AI日报「12月29日」✨✨✨✨✨✨✨✨1⃣️?️数字人工具推荐：开源且适合小白用户特点：一键安装包，无需配置环境，简单易用。功能：生成数字人视频，支持语音合成和声音克隆，操作界面中英文可选。系统兼容：支持Windows、Linux、macOS。模型支持：MuseTalk（文本到语音）、CosyVoice（语音克隆）。使用步骤：下载8G+3G语音模型包，启动模型即可。?GitHub：[https://github.com/modstart-lib/aigcpanel](https://github.com/modstart-lib/aigcpanel)?官网：[https://aigcpanel.com](https://aigcpanel.com)?[https://x.com/imxiaohu/status/1872852432549765195](https://x.com/imxiaohu/status/1872852432549765195)2⃣️?Google Veo 2：AI生成逼真的Vlog视频效果：生成的视频接近真实，几乎难以分辨。应用：适合创作和内容制作。?[https://x.com/imxiaohu/status/1872984285634019476](https://x.com/imxiaohu/status/1872984285634019476)