通义听悟是什么

通义听悟是阿里云推出的一款基于大模型的工作学习AI助手。它主要针对音视频内容提供转写、检索、摘要和整理等功能。具体来说，通义听悟可以实时记录交流内容并同步翻译、批量转写音视频文件并区分发言人、智能提炼全文概要、章节速览和发言总结、提取视频中的PPT并总结摘要、自动提取关键词和待办事项、编辑整理笔记并导出分享。通义听悟依托大模型技术，帮助用户更高效地记录、整理和分析音视频内容，提高工作和学习效率。它于2023年6月1日开始公测，并在2023年11月的云栖大会上正式上线。内容由AI大模型生成，请仔细甄别

[[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