examples/Pause-Tag.json

{"id":"b70cf6f7-8531-4faa-9843-9c963a4ba577","revision":0,"last_node_id":38,"last_link_id":49,"nodes":[{"id":21,"type":"Note","pos":[-128.1415557861328,534.7645263671875],"size":[415,88],"flags":{},"order":0,"mode":0,"inputs":[],"outputs":[],"properties":{},"widgets_values":["Use Load Text From File if you want to use a .txt file instead of text-area. You can load .txt files from ComfyUI/input, ComfyUI/output or ComfyUI/temp directories."],"color":"#432","bgcolor":"#653"},{"id":28,"type":"LoadTextFromFileNode","pos":[-65.6552963256836,428.2049865722656],"size":[289.5152282714844,58],"flags":{},"order":1,"mode":4,"inputs":[{"localized_name":"file","name":"file","type":"COMBO","widget":{"name":"file"},"link":null}],"outputs":[{"localized_name":"text","name":"text","type":"STRING","links":null}],"properties":{"Node name for S&R":"LoadTextFromFileNode","cnr_id":"VibeVoice-ComfyUI","ver":"5a24489a7b0bf0c406d291dd51e82a085d338d44"},"widgets_values":["No text files found in any directory"],"color":"#323","bgcolor":"#535"},{"id":15,"type":"LoadAudio","pos":[15.256911277770996,126.44892883300781],"size":[270,136],"flags":{},"order":2,"mode":0,"inputs":[{"localized_name":"audio","name":"audio","type":"COMBO","widget":{"name":"audio"},"link":null},{"localized_name":"audioUI","name":"audioUI","type":"AUDIO_UI","widget":{"name":"audioUI"},"link":null},{"localized_name":"upload","name":"upload","type":"AUDIOUPLOAD","widget":{"name":"upload"},"link":null}],"outputs":[{"localized_name":"AUDIO","name":"AUDIO","type":"AUDIO","links":[48]}],"properties":{"cnr_id":"comfy-core","ver":"0.3.49","Node name for S&R":"LoadAudio"},"widgets_values":["Voice.mp3",null,null],"color":"#2a363b","bgcolor":"#3f5159"},{"id":16,"type":"PreviewAudio","pos":[892.3655395507812,127.41075897216797],"size":[270,88],"flags":{},"order":6,"mode":0,"inputs":[{"localized_name":"audio","name":"audio","type":"AUDIO","link":49},{"localized_name":"audioUI","name":"audioUI","type":"AUDIO_UI","widget":{"name":"audioUI"},"link":null}],"outputs":[],"properties":{"cnr_id":"comfy-core","ver":"0.3.49","Node name for S&R":"PreviewAudio"},"widgets_values":[],"color":"#323","bgcolor":"#535"},{"id":22,"type":"Note","pos":[365.11663818359375,535.5830078125],"size":[415,88],"flags":{},"order":3,"mode":0,"inputs":[],"outputs":[],"properties":{},"widgets_values":["The first time you use a model, it will be downloaded to ComfyUI/models/vibevoice/. This can take several minutes!\nThe VibeVoice-1.5B model (about 5GB)\nThe VibeVoice-Large model (about 17GB)\nThe VibeVoice-Large-Quant-4Bit model (about 7GB)"],"color":"#432","bgcolor":"#653"},{"id":38,"type":"Note","pos":[818.8140869140625,270.3061218261719],"size":[415,88],"flags":{},"order":4,"mode":0,"inputs":[],"outputs":[],"properties":{},"widgets_values":["[pause]: add 1 second of silence.\n[pause:{number}] add {number}ms of pause\nWARNING: the pause tag forces the text to be split into chunks. This may worsen the model’s ability to understand the context. The model’s context is represented ONLY by its own chunk."],"color":"#432","bgcolor":"#653"},{"id":37,"type":"VibeVoiceSingleSpeakerNode","pos":[376.42669677734375,126.94989013671875],"size":[400,352],"flags":{},"order":5,"mode":0,"inputs":[{"localized_name":"voice_to_clone","name":"voice_to_clone","shape":7,"type":"AUDIO","link":48},{"localized_name":"text","name":"text","type":"STRING","widget":{"name":"text"},"link":null},{"localized_name":"model","name":"model","type":"COMBO","widget":{"name":"model"},"link":null},{"localized_name":"attention_type","name":"attention_type","type":"COMBO","widget":{"name":"attention_type"},"link":null},{"localized_name":"free_memory_after_generate","name":"free_memory_after_generate","type":"BOOLEAN","widget":{"name":"free_memory_after_generate"},"link":null},{"localized_name":"diffusion_steps","name":"diffusion_steps","type":"INT","widget":{"name":"diffusion_steps"},"link":null},{"localized_name":"seed","name":"seed","type":"INT","widget":{"name":"seed"},"link":null},{"localized_name":"cfg_scale","name":"cfg_scale","type":"FLOAT","widget":{"name":"cfg_scale"},"link":null},{"localized_name":"use_sampling","name":"use_sampling","type":"BOOLEAN","widget":{"name":"use_sampling"},"link":null},{"localized_name":"temperature","name":"temperature","shape":7,"type":"FLOAT","widget":{"name":"temperature"},"link":null},{"localized_name":"top_p","name":"top_p","shape":7,"type":"FLOAT","widget":{"name":"top_p"},"link":null},{"localized_name":"max_words_per_chunk","name":"max_words_per_chunk","shape":7,"type":"INT","widget":{"name":"max_words_per_chunk"},"link":null}],"outputs":[{"localized_name":"audio","name":"audio","type":"AUDIO","links":[49]}],"properties":{"Node name for S&R":"VibeVoiceSingleSpeakerNode","cnr_id":"VibeVoice-ComfyUI","ver":"5a24489a7b0bf0c406d291dd51e82a085d338d44"},"widgets_values":["Hello, this is a test of the VibeVoice text-to-speech system. [pause] Do you like my voice? [pause:500] What's your name?","VibeVoice-1.5B","auto",true,20,42,"fixed",1.3,false,0.95,0.95,250],"color":"#223","bgcolor":"#335"}],"links":[[48,15,0,37,0,"AUDIO"],[49,37,0,16,0,"AUDIO"]],"groups":[],"config":{},"extra":{"ds":{"scale":1.1000000000000005,"offset":[127.54923408733805,16.966619865757746]}},"version":0.4}