[{"data":1,"prerenderedAt":179},["ShallowReactive",2],{"repo-kittenml-kittentts-zh-CN":3,"i18n-kittenml-kittentts-zh-CN":176},{"mirrorPool":4,"detail":13,"relatedProjects":69},[5,9],{"key":6,"label":7,"base":8,"type":6},"github","mirror.github","https:\u002F\u002Fgithub.com\u002F",{"key":10,"label":11,"base":12,"type":10},"auto-proxy","mirror.autoProxy","https:\u002F\u002Fgithub.xxlab.tech\u002F",{"owner":14,"repo":15,"repoId":16,"repoUrl":17,"starCount":18,"language":19,"description":20,"languages":21,"screenshots":23,"homepage":24,"pushedAt":25,"ownerAvatar":26,"ownerName":24,"ownerBio":24,"lastSyncTime":27,"lastReleaseTime":28,"tags":29,"license":30,"category":31,"subgroup":32,"releases":33},"KittenML","KittenTTS",1032248449,"https:\u002F\u002Fgithub.com\u002FKittenML\u002FKittenTTS",16194,"Python","Open-source State-of-the-art TTS model which runs on a CPU 😻 ",{"Python":22},100,[],"","2026-10-16","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F224667585?v=4","2026-10-20T10:23:40.907347+00:00","2026-02-24T20:14:42Z",[],"Apache-2.0","ai","语音转文字工具",[34,48,58],{"tag":35,"publishAt":28,"semVer":36,"prerelease":40,"assets":41},"0.8.1",[37,38,39],0,8,1,false,[42],{"fileName":43,"sizeMb":44,"sha256":45,"downloadCount":46,"originUrl":47},"kittentts-0.8.1-py3-none-any.whl",0.02,"482a436c4f1f3192153710376e459ff3689517ebcda7c2b051e2fd4187b41851",1869400,"https:\u002F\u002Fgithub.com\u002FKittenML\u002FKittenTTS\u002Freleases\u002Fdownload\u002F0.8.1\u002Fkittentts-0.8.1-py3-none-any.whl",{"tag":49,"publishAt":50,"semVer":51,"prerelease":40,"assets":52},"0.8","2026-02-19T04:25:24Z",[37,37,37],[53],{"fileName":54,"sizeMb":44,"sha256":55,"downloadCount":56,"originUrl":57},"kittentts-0.8.0-py3-none-any.whl","cba97464da2ec56384b9fc03004449dadbe6d9abd16aa89e98953027854fd7d9",16048,"https:\u002F\u002Fgithub.com\u002FKittenML\u002FKittenTTS\u002Freleases\u002Fdownload\u002F0.8\u002Fkittentts-0.8.0-py3-none-any.whl",{"tag":59,"publishAt":60,"semVer":61,"prerelease":40,"assets":62},"0.1","2025-08-05T03:32:23Z",[37,37,37],[63],{"fileName":64,"sizeMb":65,"sha256":66,"downloadCount":67,"originUrl":68},"kittentts-0.1.0-py3-none-any.whl",0.01,"5a498422ec275f5df41b87592c6c482e637230fd563039197244d3966d1ce793",230220,"https:\u002F\u002Fgithub.com\u002FKittenML\u002FKittenTTS\u002Freleases\u002Fdownload\u002F0.1\u002Fkittentts-0.1.0-py3-none-any.whl",[70,91,110,132,147,163],{"owner":71,"repo":72,"repoId":73,"category":74,"subgroup":32,"language":75,"tags":76,"starCount":81,"ownerUid":82,"latestTag":83,"platforms":84,"lastReleaseTime":88,"downloadCount":89,"description":90},"cjpais","Handy",931888694,"tools","Rust",[77,78,79,80],"accessibility","cross-platform","speech-to-text","tauri-v2",32801,1559480,"v0.9.8",[85,86,87],"windows","mac","linux","2026-10-03T02:42:15Z",13374,"一款免费、开源、可扩展的离线语音转文字桌面应用，支持 Windows、macOS 和 Linux。",{"owner":92,"repo":93,"repoId":94,"category":31,"subgroup":32,"language":95,"tags":96,"starCount":102,"ownerUid":103,"latestTag":104,"platforms":105,"lastReleaseTime":107,"downloadCount":108,"description":109},"altic-dev","FluidVoice",1061327311,"Swift",[31,97,98,99,100,101],"dictation","ios","llama-cpp","macos","swift",12444,224717674,"v1.6.13-beta.1",[86,106],"other","2026-10-25T09:45:47Z",201,"一款macOS平台最快、支持本地AI增强的语音听写应用，是Wispr Flow的开源本地替代品。",{"owner":111,"repo":112,"repoId":113,"category":74,"subgroup":32,"language":114,"tags":115,"starCount":125,"ownerUid":126,"latestTag":127,"platforms":128,"lastReleaseTime":129,"downloadCount":130,"description":131},"OpenWhispr","openwhispr",1004647857,"JavaScript",[31,116,78,117,118,87,100,119,120,121,122,79,123,124,85],"anthropic","gemini","groq","nvidia","open-source","openai","parakeet","transcribe","whisper",9741,254803777,"v1.10.4",[85,86,87],"2026-10-22T08:21:23Z",4473,"一款隐私优先的跨平台语音转文字应用，支持本地（NVIDIA Parakeet\u002FWhisper）和云端模型，可进行会议转录和AI代理交互。",{"owner":133,"repo":134,"repoId":135,"category":31,"subgroup":32,"language":136,"tags":137,"starCount":140,"ownerUid":141,"latestTag":142,"platforms":143,"lastReleaseTime":144,"downloadCount":145,"description":146},"thewh1teagle","vibe",740293013,"TypeScript",[31,78,138,121,139,123,124],"desktop","rust",7743,61390950,"v3.2.2",[85,86,87],"2026-09-05T13:24:57Z",62026,"一款注重隐私的本地AI转录应用，基于OpenAI的Whisper模型，可在设备上转录音视频。",{"owner":148,"repo":148,"repoId":149,"category":74,"subgroup":32,"language":150,"tags":151,"starCount":156,"ownerUid":157,"latestTag":158,"platforms":159,"lastReleaseTime":160,"downloadCount":161,"description":162},"espeak-ng",47648456,"C",[152,153,148,154,155],"android","espeak","speech-synthesis","text-to-speech",6910,16214005,"1.52.0",[85,152],"2024-12-12T13:47:27Z",291601,"一款开源的紧凑型语音合成器（TTS），支持100多种语言和口音，采用共振峰合成方法，提供命令行、共享库和SAPI5等多种使用方式。",{"owner":164,"repo":165,"repoId":166,"category":74,"subgroup":32,"language":95,"tags":167,"starCount":169,"ownerUid":170,"latestTag":171,"platforms":172,"lastReleaseTime":173,"downloadCount":174,"description":175},"Beingpax","VoiceInk",875661263,[100,168,101],"macos-app",6720,101010368,"v2.22",[86],"2026-10-01T09:16:53Z",534,"macOS上Superwhisper和Wispr Flow的最佳开源替代品，一款无订阅的语音转文字应用，支持离线本地模型、智能上下文感知、全局快捷键和AI助手模式。",{"description":177,"readmeHtml":178},"KittenTTS 是一个开源文本转语音库（Python），旗舰模型 KittenTTS 2 只需约 5 秒参考音频即可克隆音色，支持表情控制与 20 种语言，可在 CPU 上实时合成语音。","\u003Ch2 id=\"项目概述\">项目概述\u003C\u002Fh2>\u003Cp>KittenTTS 是一个开源文本转语音库。旗舰模型 KittenTTS 2 是一个 1.7B 参数的 1-bit 语音语言模型，只需约 5 秒参考音频就能克隆任意说话人的音色，还支持情绪标签与重读控制。它同时保留 15M 到 80M 参数的轻量 ONNX 模型，纯 CPU 即可运行，无需 GPU 就能实时合成 24 kHz 语音。\u003C\u002Fp>\n\u003Cblockquote>\n\u003Cp>声音克隆与轻量部署兼顾，CPU 也能实时开口说话。\u003C\u002Fp>\n\u003C\u002Fblockquote>\n\u003Ctable>\n\u003Cthead>\n\u003Ctr>\n\u003Cth>项目\u003C\u002Fth>\n\u003Cth>内容\u003C\u002Fth>\n\u003C\u002Ftr>\n\u003C\u002Fthead>\n\u003Ctbody>\u003Ctr>\n\u003Ctd>平台\u003C\u002Ftd>\n\u003Ctd>Linux、macOS、Windows（CPU 或 GPU）\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>语言\u003C\u002Ftd>\n\u003Ctd>Python\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>许可\u003C\u002Ftd>\n\u003Ctd>Apache-2.0\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>输出采样率\u003C\u002Ftd>\n\u003Ctd>24 kHz\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftbody>\u003C\u002Ftable>\n\u003Ch2 id=\"主要功能\">主要功能\u003C\u002Fh2>\u003Cul>\n\u003Cli>\u003Cstrong>声音克隆\u003C\u002Fstrong>：5-30 秒单人音频即可复刻音色，无需微调\u003C\u002Fli>\n\u003Cli>\u003Cstrong>内置音色\u003C\u002Fstrong>：47 个预置音色，含 9 个非英语音色\u003C\u002Fli>\n\u003Cli>\u003Cstrong>多语种合成\u003C\u002Fstrong>：支持中、英、日、韩、法、德等 20 种语言\u003C\u002Fli>\n\u003Cli>\u003Cstrong>表情控制\u003C\u002Fstrong>：情绪标签、事件标签与重读括号三种方式\u003C\u002Fli>\n\u003Cli>\u003Cstrong>解码预设\u003C\u002Fstrong>：在稳定性与表现力之间按请求权衡\u003C\u002Fli>\n\u003Cli>\u003Cstrong>长文本处理\u003C\u002Fstrong>：按句分块拼接，适合文章级朗读\u003C\u002Fli>\n\u003Cli>\u003Cstrong>文本预处理\u003C\u002Fstrong>：数字、货币、日期、缩写自动展开朗读\u003C\u002Fli>\n\u003Cli>\u003Cstrong>轻量模型\u003C\u002Fstrong>：15M-80M ONNX 模型，无 GPU 也能跑\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2 id=\"适用人群\">适用人群\u003C\u002Fh2>\u003Cul>\n\u003Cli>为应用添加语音朗读功能的开发者\u003C\u002Fli>\n\u003Cli>需要克隆特定音色的内容创作者\u003C\u002Fli>\n\u003Cli>在低配设备或边缘环境做语音合成的工程师\u003C\u002Fli>\n\u003Cli>制作有声内容与配音的团队\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2 id=\"快速上手\">快速上手\u003C\u002Fh2>\u003Col>\n\u003Cli>安装：\u003C\u002Fli>\n\u003C\u002Fol>\n\u003Cdiv class=\"code-block\">\u003Cpre>\u003Ccode class=\"hljs language-bash\">pip install kittenml\u003C\u002Fcode>\u003C\u002Fpre>\u003C\u002Fdiv>\u003Col start=\"2\">\n\u003Cli>合成语音：\u003C\u002Fli>\n\u003C\u002Fol>\n\u003Cdiv class=\"code-block\">\u003Cpre>\u003Ccode class=\"hljs language-python\">from kittenml import KittenTTS\n\nm = KittenTTS('KittenML\u002Fkitten-tts-2')\naudio = m.generate('你好，世界', voice='Bruno')\u003C\u002Fcode>\u003C\u002Fpre>\u003C\u002Fdiv>\u003Col start=\"3\">\n\u003Cli>克隆音色时把 voice 参数换成 reference，传入参考音频：\u003C\u002Fli>\n\u003C\u002Fol>\n\u003Cdiv class=\"code-block\">\u003Cpre>\u003Ccode class=\"hljs language-python\">audio = m.generate('这是克隆的声音', reference='my_voice.wav')\u003C\u002Fcode>\u003C\u002Fpre>\u003C\u002Fdiv>\u003Col start=\"4\">\n\u003Cli>轻量模型通过同一个 KittenTTS 构造器加载，无需额外安装\u003C\u002Fli>\n\u003C\u002Fol>\n\u003Ch2 id=\"核心优势\">核心优势\u003C\u002Fh2>\u003Cul>\n\u003Cli>\u003Cstrong>无 GPU 可用\u003C\u002Fstrong>：轻量模型纯 CPU 运行，旗舰模型也有 CPU 路径\u003C\u002Fli>\n\u003Cli>\u003Cstrong>克隆门槛低\u003C\u002Fstrong>：几秒音频、无需训练即可复刻音色\u003C\u002Fli>\n\u003Cli>\u003Cstrong>安装极简\u003C\u002Fstrong>：单包安装，权重随用随下，无需登录 Hugging Face\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2 id=\"系统要求\">系统要求\u003C\u002Fh2>\u003Ctable>\n\u003Cthead>\n\u003Ctr>\n\u003Cth>项目\u003C\u002Fth>\n\u003Cth>要求\u003C\u002Fth>\n\u003C\u002Ftr>\n\u003C\u002Fthead>\n\u003Ctbody>\u003Ctr>\n\u003Ctd>操作系统\u003C\u002Ftd>\n\u003Ctd>Linux、macOS、Windows\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>语言环境\u003C\u002Ftd>\n\u003Ctd>Python 3.9+\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>硬件\u003C\u002Ftd>\n\u003Ctd>GPU 约 8 GB 显存，或 CPU 约 6 GB 内存\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftbody>\u003C\u002Ftable>\n\u003Ch2 id=\"注意事项\">注意事项\u003C\u002Fh2>\u003Cul>\n\u003Cli>\u003Cstrong>克隆素材\u003C\u002Fstrong>：参考音频需为 5-30 秒的单人录音，混入多人会明显降低相似度\u003C\u002Fli>\n\u003Cli>\u003Cstrong>权重选择\u003C\u002Fstrong>：默认权重 947 MiB 无损，\u003Ccode>weights=emb4\u003C\u002Fcode> 体积减半但质量略降\u003C\u002Fli>\n\u003Cli>\u003Cstrong>旧版兼容\u003C\u002Fstrong>：0.8 时代的 8 个音色在新模型中原样保留，旧代码无需改动\u003C\u002Fli>\n\u003C\u002Ful>\n",1793197885764]