[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-detail:ZX20250831_94622855":3},{"code":4,"data":5},0,{"unicode":6,"title":7,"categoryId":8,"categoryName":9,"industryId":10,"industryName":11,"origin":12,"originAuthor":13,"originRemark":14,"originUrl":15,"pic":16,"content":17,"numRead":18,"numLike":4,"createTime":19,"hadFav":4,"hadLike":4,"status":4,"memberUnicode":20,"companyLogo":21,"companyName":22,"corporateVideoUrl":13,"collected":4,"corporate3dCover":23,"corporate3dUrl":23,"corporate3dId":23,"companyUnicode":24,"focusFlag":25,"exhibitionMainInfoVO":23},"ZX20250831_94622855","微软解锁AI配音新技能：最长90秒多角色叙述，语音更像真人","1242381412612444162","行业动态","1245513623956107264","其它行业",1,"","http:\u002F\u002Ftech.ifeng.com\u002F","https:\u002F\u002Ftech.ifeng.com\u002Fc\u002F8mF0Wlq7kcf","https:\u002F\u002Fx0.ifengimg.com\u002Fres\u002F2025\u002F06FDA3648103819DFF42BEAEEBFA5316B24127AF_size71_w1920_h1080.jpg","\u003Cdiv class=\"index_articleBox_6mBbT\" style=\"height:auto\">\n \u003Cdiv class=\"index_text_D0U1y\">\n  \u003Cp>IT之家 8 月 30 日消息，科技媒体 Windows Latest 昨日（8 月 29 日）发布博文，报道称微软在 Copilot Labs 推出全新 AI 语音生成工具 Copilot Audio Expressions，\u003Cstrong>可通过 Emotive 和 Story 两种模式生成更具情感的英文语音。\u003C\u002Fstrong>\u003C\u002Fp>\n  \u003Cp class=\"textAlignCenter\">\u003Cimg class=\"empty_bg\" src=\"https:\u002F\u002Fx0.ifengimg.com\u002Fres\u002F2025\u002F06FDA3648103819DFF42BEAEEBFA5316B24127AF_size71_w1920_h1080.jpg\" src=\"data:image\u002Fpng;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABAQMAAAAl21bKAAAAA1BMVEXy8vJkA4prAAAACklEQVQI12NgAAAAAgAB4iG8MwAAAABJRU5ErkJggg==\" style=\" width: 640px; height: 360px;\">\u003C\u002Fp>\n  \u003Cp>IT之家注：Copilot Audio Expressions 是一款 AI 语音生成工具，功能是让输出的音频更接近真人，并可根据需求加入创意润色。用户无需注册即可直接体验，并可下载 MP3 格式音频，方便在任何设备播放。\u003C\u002Fp>\n  \u003Cp>该工具目前提供 Emotive（情感表达）和 Story（故事创作）两种模式。\u003C\u002Fp>\n  \u003Cp class=\"textAlignCenter\">\u003Cimg class=\"empty_bg\" src=\"https:\u002F\u002Fx0.ifengimg.com\u002Fres\u002F2025\u002FB545BBE622A9C0BB04653A7FBAA0AE8E818B2B45_size80_w2048_h908.jpg\" src=\"data:image\u002Fpng;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABAQMAAAAl21bKAAAAA1BMVEXy8vJkA4prAAAACklEQVQI12NgAAAAAgAB4iG8MwAAAABJRU5ErkJggg==\" style=\" width: 640px; height: 283px;\">\u003C\u002Fp>\n  \u003Cp>该媒体在测试 Emotive 模式后，选用“Oak”音色和“narration”叙述风格，将模拟火车站的脚本输入系统。\u003C\u002Fp>\n  \u003Cp class=\"textAlignCenter\">\u003Cimg class=\"empty_bg\" src=\"https:\u002F\u002Fx0.ifengimg.com\u002Fres\u002F2025\u002F50FE906264F3066411454AAA0FEDA6AF4A57FDBC_size134_w1440_h833.jpg\" src=\"data:image\u002Fpng;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABAQMAAAAl21bKAAAAA1BMVEXy8vJkA4prAAAACklEQVQI12NgAAAAAgAB4iG8MwAAAABJRU5ErkJggg==\" style=\" width: 640px; height: 370px;\">\u003C\u002Fp>\n  \u003Cp>生成的音频不仅朗读了文字，还自动增添细节、调整措辞，让表达更生动。单段音频最长 59 秒，支持十余种声音与风格组合。\u003C\u002Fp>\n  \u003Cp>在 Story 模式下，系统自动选择音色和风格，用户仅需提供主题提示。\u003C\u002Fp>\n  \u003Cp class=\"textAlignCenter\">\u003Cimg class=\"empty_bg\" src=\"https:\u002F\u002Fx0.ifengimg.com\u002Fres\u002F2025\u002F415A1EDCC9AF7DE6EA5C7046C702878DEF4E4765_size95_w1504_h914.jpg\" src=\"data:image\u002Fpng;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABAQMAAAAl21bKAAAAA1BMVEXy8vJkA4prAAAACklEQVQI12NgAAAAAgAB4iG8MwAAAABJRU5ErkJggg==\" style=\" width: 640px; height: 388px;\">\u003C\u002Fp>\n  \u003Cp>例如输入“讲一个猫在暗处潜行觅食的故事”，AI 就生成了一个长达 90 秒的多角色叙述：旁白用美式口音，猫的对白则为英式口音，并巧妙穿插互动，形成自然流畅的对话效果。\u003C\u002Fp>\n  \u003Cp>测试结果表明，Story 模式在情节构建、角色区分及声音融合度方面表现出色，输出的成品不像单调的机器朗读，更像是一次配音合作，让该工具不仅适用于简单朗诵，也可胜任有多角色的创意作品制作。\u003C\u002Fp>\n  \u003Cp>该工具目前仅支持英文，中文及其他语言用户暂无法直接生成母语音频，微软尚未透露后续是否会增加多语言支持。\u003C\u002Fp>\n \u003C\u002Fdiv>\n \u003Cspan>\u003C\u002Fspan>\n \u003Cdiv class=\"index_end_1O-ki\">\u003C\u002Fdiv>\n\u003C\u002Fdiv>",405,"2025-09-01 11:43:47","3620375967","https:\u002F\u002Foss-images6396289.yzdli.com\u002F3620375967\u002F1ftirt8q0e\u002F20200602111616.png","广州立佳信科技有限责任公司",null,"ci67fdmkbnogt",-2]