{"kind":"guides","slug":"comfyui-text-to-speech","path":"/guides/comfyui-text-to-speech","title":"ComfyUI TTS：节点与角色配音 | SuperClonica","description":"ComfyUI 文本转语音：TTS Audio Suite 等节点包，以及如何用 Load Audio 和 Create Video 节点把做好的英语等语言角色配音加入工作流。","h1":"ComfyUI 文本转语音：TTS 节点与添加配音","intro":"ComfyUI 能在工作流中处理音频，而文本转语音通常来自自定义节点包。这适合克隆和实验，但模型可能很大，还会和图像模型争用显存。本页介绍的 SuperClonica 引擎不支持中文，可朗读英语、日语等 31 种语言。\n\n本指南介绍节点方案，以及更简单的方案：先把声音做成文件，再载入工作流。","sections":[{"heading":"ComfyUI 中的 TTS 节点","paragraphs":["最知名的节点包是 TTS Audio Suite。可通过 ComfyUI Manager 安装，或克隆到 ComfyUI/custom_nodes 并按步骤安装。它把多种引擎放在同一组节点后面，包括 ChatterboxTTS、F5-TTS、Higgs Audio、MOSS-TTS 和 Echo-TTS，还有 RVC 变声。模型可能有好几 GB，各引擎的许可也不同，商用前请先阅读。"]},{"heading":"什么时候现成的声音更简单","paragraphs":["节点包适合克隆声音或需要引擎的特殊控制。如果只需要一段做好的配音，就不必在 ComfyUI 内运行。免费的 SuperClonica 引擎在普通处理器上运行，把显卡留给图像和视频模型。SuperClonica 没有 ComfyUI 专用节点，两者通过音频文件衔接。"]},{"heading":"制作音频文件","paragraphs":["从声音库约 190 个声音中选择，从旁白到游戏和电影角色，都可以在其页面免费试听 30 到 100 个字符的句子。整段脚本可用 python -m pip install superclonica-cpu 安装引擎，然后运行：superclonica --text-file script.txt --voice F2 --lang en --output voice.wav。首次运行会下载一次模型，约 400 MB，之后可离线使用。"]},{"heading":"载入工作流","paragraphs":["把 voice.wav 放进 ComfyUI/input 文件夹，添加会读取该文件夹的 Load Audio 节点。连接到 Preview Audio 即可试听。要加入视频，把 Load Audio 连接到 Create Video 的可选音频输入，并连上画面帧，再把结果送到 Save Video。"]},{"heading":"让声音和画面同步","paragraphs":["先生成配音，再按其长度生成画面：文件时长除以每帧时间，就是所需帧数。多个场景时，每句台词单独做一个文件。语速可用引擎的 --speed 调整，数值越大越快。"]}],"faq":[{"question":"ComfyUI 内置文本转语音吗？","answer":"其核心有加载、试听和保存音频的节点。文本转语音通常来自 TTS Audio Suite 等节点包。"},{"question":"ComfyUI 最好的 TTS 节点是什么？","answer":"取决于用途。TTS Audio Suite 提供许多适合克隆和实验的引擎。若只需快速配音，在 ComfyUI 外制作文件往往更简单。"},{"question":"有 SuperClonica 节点吗？","answer":"没有。用免费引擎生成 WAV 文件，再通过 Load Audio 载入。"},{"question":"可以把声音加到生成的视频里吗？","answer":"可以：把 Load Audio 连接到 Create Video 的音频输入，然后使用 Save Video。"},{"question":"配音需要显卡吗？","answer":"SuperClonica 不需要：引擎在普通处理器上运行。"}],"cta":{"catalog":"浏览声音","install":"安装 SuperClonica 引擎"},"sources":[{"label":"TTS Audio Suite for ComfyUI","url":"https://github.com/diodiogod/TTS-Audio-Suite"},{"label":"ComfyUI audio nodes (source)","url":"https://github.com/Comfy-Org/ComfyUI/blob/master/comfy_extras/nodes_audio.py"},{"label":"ComfyUI video nodes (source)","url":"https://github.com/Comfy-Org/ComfyUI/blob/master/comfy_extras/nodes_video.py"},{"label":"SuperClonica engine on PyPI","url":"https://pypi.org/project/superclonica-cpu/"}],"published":"2026-11-01","updated":"2026-11-01","pages":[{"slug":"windows-speech-voices","path":"/guides/windows-speech-voices","h1":"在 Windows 中添加文字转语音声音和语音包"},{"slug":"character-ai-text-to-speech","path":"/guides/character-ai-text-to-speech","h1":"Character AI 文字转语音：应用内外的声音"},{"slug":"keynote-ai-voiceover","path":"/guides/keynote-ai-voiceover","h1":"Keynote AI 旁白：在 Mac 上为幻灯片配音"},{"slug":"capcut-text-to-speech","path":"/guides/capcut-text-to-speech","h1":"为 CapCut 文字转语音加入角色声音"},{"slug":"kinemaster-text-to-speech","path":"/guides/kinemaster-text-to-speech","h1":"KineMaster 文字转语音：为剪辑添加旁白"},{"slug":"adobe-express-text-to-speech","path":"/guides/adobe-express-text-to-speech","h1":"Adobe Express 文字转语音：为设计添加配音"},{"slug":"pictory-voiceover","path":"/guides/pictory-voiceover","h1":"Pictory 配音：AI 声音或你自己的声音"},{"slug":"audio-description-voice","path":"/guides/audio-description-voice","h1":"用 AI 声音为视频制作口述影像"},{"slug":"wordpress-text-to-speech","path":"/guides/wordpress-text-to-speech","h1":"不用插件的 WordPress 文字转语音：为每篇文章配上音频版"},{"slug":"talking-clock-voice","path":"/guides/talking-clock-voice","h1":"报时钟声音：用任意声音自制会说话的时钟"},{"slug":"alltalk-tts-alternative","path":"/guides/alltalk-tts-alternative","h1":"适用于 Mac 和普通 CPU 的 AllTalk TTS 替代方案"},{"slug":"sillytavern-tts","path":"/guides/sillytavern-tts","h1":"SillyTavern TTS：启用并为每个角色配音"}],"related":[{"slug":"text-to-speech","path":"/text-to-speech","h1":"在自己电脑上运行的语音合成"},{"slug":"supertonic","path":"/compare/supertonic","h1":"Supertonic 与 SuperClonica：同一模型，更快更干净"},{"slug":"fish-audio","path":"/compare/fish-audio","h1":"Fish Audio、Fish Speech 与 SuperClonica 对比"},{"slug":"omnivoice","path":"/compare/omnivoice","h1":"OmniVoice 与 SuperClonica：语言更多，还是速度更快"},{"slug":"qwen3-tts","path":"/compare/qwen3-tts","h1":"本地语音合成：Qwen3-TTS 还是 SuperClonica"},{"slug":"voxcpm","path":"/compare/voxcpm","h1":"VoxCPM 2 与 SuperClonica：录音棚音质还是 CPU 速度"},{"slug":"f5-tts","path":"/compare/f5-tts","h1":"F5-TTS 与 SuperClonica：零样本克隆还是 CPU 上的快速合成"},{"slug":"elevenlabs","path":"/compare/elevenlabs","h1":"可离线使用的 ElevenLabs 替代方案"},{"slug":"kokoro","path":"/compare/kokoro","h1":"Kokoro TTS 与 SuperClonica：两个小模型的本地语音合成"},{"slug":"piper","path":"/compare/piper","h1":"Piper TTS 与 SuperClonica：小设备还是定制音色"},{"slug":"xtts","path":"/compare/xtts","h1":"Coqui XTTS-v2 与 SuperClonica：Coqui TTS 的替代方案"},{"slug":"chatterbox","path":"/compare/chatterbox","h1":"Chatterbox TTS 与 SuperClonica：即时克隆还是训练好的音色文件"}]}