http://shenzjd.comhttp://shenzjd.com/posts/5703http://shenzjd.com/posts/5703Thu, 02 Jul 2026 19:04:36 GMT<div class="image-list-container image-list-odd"> <button type="button" class="image-preview-button image-preview-wrap" popovertarget="modal-5703-0" popovertargetaction="show" aria-label="Open image preview: #VoxCPM #文本转语音 #声音克隆 #无分词器架构 #开源AI #TGAgentVoxCPM是开源AI文本转语音模型，采用无分词器架构，支持零样本声音克隆，仅需一段参考音频即可复刻对应音色的音色、口音、情绪、语速等特征，可生成上下文感知的连续语音"> <img src="/static/https://cdn5.telesco.pe/file/Bq1AfI_TUPg-5qn05DiA9_pzuFrRSqDsL35CE32W-8cSNLePIrW9oJVoGq5ijjLPJEq1ttUrViDWDnPa5CF8Jq9pSSQAGrlksmzbZHIUO3pdvbWuLpGGtAgJu9zRpEfF9ygGHoF6kaMwoKBWe3ywpO4Qg0h30z34G053F5rTU3wbxlTsfdAHTg7_d-xXA3oIAPwABqhLZePCQQyaWSXpMOPMUvpZM-FcYT-ipcfcjgqHWyezwNE0d8HvXdyVUTph653-HaoqdZI92TZseR13Pz95mUPanj78Dcm3NyYOrWU1JH6jj1eHqPBd7Z2vSH3BPjufZcY7tU1ddg9U2zDWaA.jpg" alt="#VoxCPM #文本转语音 #声音克隆 #无分词器架构 #开源AI #TGAgentVoxCPM是开源AI文本转语音模型，采用无分词器架构，支持零样本声音克隆，仅需一段参考音频即可复刻对应音色的音色、口音、情绪、语速等特征，可生成上下文感知的连续语音" width="800" height="384" loading="eager" /> </button> <div class="modal" id="modal-5703-0" popover="auto" aria-label="Image preview"> <button type="button" class="modal__backdrop" popovertarget="modal-5703-0" popovertargetaction="hide" aria-label="Close image preview"></button> <button type="button" class="modal__close" popovertarget="modal-5703-0" popovertargetaction="hide" aria-label="Close image preview">×</button> <div class="modal__surface"> </div> </div> </div><a href="/search/result?q=%23VoxCPM" title="#VoxCPM">#VoxCPM</a> <a href="/search/result?q=%23%E6%96%87%E6%9C%AC%E8%BD%AC%E8%AF%AD%E9%9F%B3" title="#文本转语音">#文本转语音</a> <a href="/search/result?q=%23%E5%A3%B0%E9%9F%B3%E5%85%8B%E9%9A%86" title="#声音克隆">#声音克隆</a> <a href="/search/result?q=%23%E6%97%A0%E5%88%86%E8%AF%8D%E5%99%A8%E6%9E%B6%E6%9E%84" title="#无分词器架构">#无分词器架构</a> <a href="/search/result?q=%23%E5%BC%80%E6%BA%90AI" title="#开源AI">#开源AI</a> <a href="/search/result?q=%23TGAgent" title="#TGAgent">#TGAgent</a><br /><br />VoxCPM是开源AI文本转语音模型，采用无分词器架构，支持零样本声音克隆，仅需一段参考音频即可复刻对应音色的音色、口音、情绪、语速等特征，可生成上下文感知的连续语音。该模型支持流式合成，覆盖30种语言，最高可输出48kHz高品质音频，适用于AI配音、有声书、播客、数字助手等场景，完全免费开源。<br /><br /><a href="https://voxcpm.com/zh" target="_blank" rel="noopener" title="https://voxcpm.com/zh">https://voxcpm.com/zh</a><br /><a href="https://huggingface.co/spaces/openbmb/VoxCPM-Demo" target="_blank" rel="noopener" title="https://huggingface.co/spaces/openbmb/VoxCPM-Demo">https://huggingface.co/spaces/openbmb/VoxCPM-Demo</a><br /><a href="https://github.com/OpenBMB/VoxCPM" target="_blank" rel="noopener" title="https://github.com/OpenBMB/VoxCPM">https://github.com/OpenBMB/VoxCPM</a><br /><br /><i class="emoji"><b>📡</b></i> 来源：<a href="https://t.me/shenzjd_com" target="_blank" title="@shenzjd_com">@shenzjd_com</a>http://shenzjd.com/posts/5587http://shenzjd.com/posts/5587Fri, 26 Jun 2026 19:05:35 GMT<div class="image-list-container image-list-odd"> <button type="button" class="image-preview-button image-preview-wrap" popovertarget="modal-5587-0" popovertargetaction="show" aria-label="Open image preview: #dots.tts #文本转语音 #语音克隆 #本地部署 #可商用 #TGAgent本次更新发布dots.tts文本转语音克隆整合包，仅需数秒录音即可克隆音色，支持多语言输出与语气复刻，可免费商用"> <img src="/static/https://cdn5.telesco.pe/file/qNQkqKqb0Thwr0ifbbpWjBRA-JE0u3eHwoZ14brwDGhKDNU_wb2m2t3_3-oFiUsdb05WjPblKS-mzuM0L8__RJgnit2irqskXuEv-bPQ-JFkInJmAqpbm_FYzVObNh8dmVhT2XEvVVLxeA05aVOPIhhcOyVY4mumI4tTwZmMED7IEhjBYqCYXpeqf6dG6Hse4KTkihM5BMW1TtyMbhqAmcTJRmmNJnuxQ83RI_LTp71TyPI3xSKc1AbbEftUTAEGVXbsTefP0mwZN22kHaqvXKpYuVMx6EznryB1mnrTCkuw2be5aTgFjP0EJdmKLl9laouErBYvZ2jKH3YCzti0Fg.jpg" alt="#dots.tts #文本转语音 #语音克隆 #本地部署 #可商用 #TGAgent本次更新发布dots.tts文本转语音克隆整合包，仅需数秒录音即可克隆音色，支持多语言输出与语气复刻，可免费商用" width="800" height="419" loading="eager" /> </button> <div class="modal" id="modal-5587-0" popover="auto" aria-label="Image preview"> <button type="button" class="modal__backdrop" popovertarget="modal-5587-0" popovertargetaction="hide" aria-label="Close image preview"></button> <button type="button" class="modal__close" popovertarget="modal-5587-0" popovertargetaction="hide" aria-label="Close image preview">×</button> <div class="modal__surface"> </div> </div> </div><a href="/search/result?q=%23dots" title="#dots">#dots</a>.tts <a href="/search/result?q=%23%E6%96%87%E6%9C%AC%E8%BD%AC%E8%AF%AD%E9%9F%B3" title="#文本转语音">#文本转语音</a> <a href="/search/result?q=%23%E8%AF%AD%E9%9F%B3%E5%85%8B%E9%9A%86" title="#语音克隆">#语音克隆</a> <a href="/search/result?q=%23%E6%9C%AC%E5%9C%B0%E9%83%A8%E7%BD%B2" title="#本地部署">#本地部署</a> <a href="/search/result?q=%23%E5%8F%AF%E5%95%86%E7%94%A8" title="#可商用">#可商用</a> <a href="/search/result?q=%23TGAgent" title="#TGAgent">#TGAgent</a><br /><br />本次更新发布dots.tts文本转语音克隆整合包，仅需数秒录音即可克隆音色，支持多语言输出与语气复刻，可免费商用。该工具需8G显存本地部署，相关资源可通过夸克网盘、索引bot或指定站点获取。<br /><br /><a href="https://pan.quark.cn/s/5ecad440bdb6" target="_blank" rel="noopener" title="https://pan.quark.cn/s/5ecad440bdb6">https://pan.quark.cn/s/5ecad440bdb6</a><br /><a href="http://noiseyp.top/" target="_blank" rel="noopener" title="http://noiseyp.top">http://noiseyp.top</a><br /><a href="http://pansou.noisework.cn/" target="_blank" rel="noopener" title="http://pansou.noisework.cn">http://pansou.noisework.cn</a><br /><br /><i class="emoji"><b>📡</b></i> 来源：<a href="https://t.me/shenzjd_com" target="_blank" title="@shenzjd_com">@shenzjd_com</a>http://shenzjd.com/posts/5181http://shenzjd.com/posts/5181Tue, 02 Jun 2026 01:36:26 GMT<a href="/search/result?q=%23MOSS" title="#MOSS">#MOSS</a> <a href="/search/result?q=%23%E6%96%87%E6%9C%AC%E8%BD%AC%E8%AF%AD%E9%9F%B3" title="#文本转语音">#文本转语音</a> <a href="/search/result?q=%23%E5%A4%9A%E8%AF%AD%E8%A8%80" title="#多语言">#多语言</a> <a href="/search/result?q=%23TGAgent" title="#TGAgent">#TGAgent</a><br /><br />MOSS-TTS-Nano 是一个多语言文本转语音模型，支持实时语音克隆、CPU部署和48kHz立体声输出，覆盖20种语言。<br /><br /><a href="https://openmoss.github.io/MOSS-TTS-Nano-Demo" target="_blank" rel="noopener" title="https://openmoss.github.io/MOSS-TTS-Nano-Demo">https://openmoss.github.io/MOSS-TTS-Nano-Demo</a><br /><br /><i class="emoji"><b>📡</b></i> 来源：<a href="https://t.me/shenzjd_com" target="_blank" title="@shenzjd_com">@shenzjd_com</a><a class="tgme_widget_message_link_preview" href="http://openmoss.github.io/MOSS-TTS-Nano-Demo" target="_blank" rel="noopener" title="MOSS-TTS-Nano is a multilingual tiny speech generation model for realtime voice cloning, CPU-friendly deployment, and lightweight product integration."> <div class="link_preview_site_name accent_color">openmoss.ai</div> <div class="link_preview_title">MOSS-TTS-Nano | Multilingual Speech Generation</div> <div class="link_preview_description">MOSS-TTS-Nano is a multilingual tiny speech generation model for realtime voice cloning, CPU-friendly deployment, and lightweight product integration.</div> </a>http://shenzjd.com/posts/4829http://shenzjd.com/posts/4829Fri, 29 May 2026 01:42:53 GMT<a href="/search/result?q=%23%E5%AD%97%E5%B9%95%E9%85%8D%E9%9F%B3" title="#字幕配音">#字幕配音</a> <a href="/search/result?q=%23AI%E5%90%88%E6%88%90" title="#AI合成">#AI合成</a> <a href="/search/result?q=%23%E6%96%87%E6%9C%AC%E8%BD%AC%E8%AF%AD%E9%9F%B3" title="#文本转语音">#文本转语音</a> <a href="/search/result?q=%23TelegramDigest" title="#TelegramDigest">#TelegramDigest</a><br /><br />FlowSpeech更新，新增上下文感知文本转语音工具，支持情绪与停顿控制，提供30+声线。<br /><br /><a href="https://flowspeech.io/zh" target="_blank" rel="noopener" title="https://flowspeech.io/zh">https://flowspeech.io/zh</a><br /><br /><i class="emoji"><b>📡</b></i> 来源：<a href="https://t.me/shenzjd_com" target="_blank" title="@shenzjd_com">@shenzjd_com</a><a class="tgme_widget_message_link_preview" href="https://flowspeech.io/zh" target="_blank" rel="noopener" title="FlowSpeech 是一款上下文感知的文本转语音工具，将文本转换为拟人 AI 语音，支持情绪与停顿控制，提供 30+ 声线，输出专业级 TTS 语音合成。"> <div class="link_preview_site_name accent_color">FlowSpeech</div> <img class="link_preview_image" alt="免费文字转语音 (Text to Speech) 拟人 AI 声音 | FlowSpeech" src="/static/https://cdn4.telesco.pe/file/RbCuhoPkk-GUxm6-hdyp1x71uqDdfegZQO77AOH6bbGuOY2NmDSIpIQK6yIoDXBGc0NA103F67LZuZcgMZ732-6rjCfFWkVfxuZ2lTQMypmPHHfh74E5_QOx5XzCmMUzTRYcQIxMqmpf8qG-H5_P8CZ00Cx2Lxk9Ma_t8e-bJLCM4R2ts4Yv1RAMSbV0Qt0BBRlQo88sTimZTAoudh1V3IIl_6CAf_LQKN_yr47DiS0O1Eppbo-wz7DhCKHiyxuh-ZNQ6A85ftyJ3zxm6t5JAGA7t3gVX0aBuF29-zb5K394Vioo3NI38-BjtAq5V5BOKjyts0XCqJ1Z-CYM3qc_OA.jpg" width="1200" height="630" loading="eager" /> <div class="link_preview_title">免费文字转语音 (Text to Speech) 拟人 AI 声音 | FlowSpeech</div> <div class="link_preview_description">FlowSpeech 是一款上下文感知的文本转语音工具，将文本转换为拟人 AI 语音，支持情绪与停顿控制，提供 30+ 声线，输出专业级 TTS 语音合成。</div> </a>