{"id":18879180,"url":"https://github.com/aifsh/comfyui-xtts","last_synced_at":"2025-08-20T20:32:59.345Z","repository":{"id":238809788,"uuid":"797539342","full_name":"AIFSH/ComfyUI-XTTS","owner":"AIFSH","description":"a custom comfyui node for coqui-ai/TTS's xtts module! support 17 languages voice cloning and tts","archived":false,"fork":false,"pushed_at":"2024-06-24T09:45:59.000Z","size":867,"stargazers_count":46,"open_issues_count":8,"forks_count":11,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-12-19T03:03:03.453Z","etag":null,"topics":["comfyui","tts","voicecloning","xttsv2"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mpl-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AIFSH.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-05-08T03:20:56.000Z","updated_at":"2024-11-25T07:15:25.000Z","dependencies_parsed_at":"2024-05-08T09:27:30.476Z","dependency_job_id":"993e414e-9aed-4d92-9c9a-3b27fb2e707f","html_url":"https://github.com/AIFSH/ComfyUI-XTTS","commit_stats":null,"previous_names":["aifsh/comfyui-xtts"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AIFSH%2FComfyUI-XTTS","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AIFSH%2FComfyUI-XTTS/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AIFSH%2FComfyUI-XTTS/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AIFSH%2FComfyUI-XTTS/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AIFSH","download_url":"https://codeload.github.com/AIFSH/ComfyUI-XTTS/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":230454430,"owners_count":18228392,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["comfyui","tts","voicecloning","xttsv2"],"created_at":"2024-11-08T06:33:56.680Z","updated_at":"2024-12-19T15:09:49.663Z","avatar_url":"https://github.com/AIFSH.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ComfyUI-XTTS\na custom comfyui node for [coqui-ai/TTS](https://github.com/coqui-ai/TTS.git)'s xtts module! support 17 languages voice cloning and tts\n\n English (en), Spanish (es), French (fr), German (de), Italian (it), Portuguese (pt), Polish (pl), Turkish (tr), Russian (ru), Dutch (nl), Czech (cs), Arabic (ar), Chinese (zh-cn), Japanese (ja), Hungarian (hu), Korean (ko) Hindi (hi)\n\n\u003cdiv\u003e\n  \u003cfigure\u003e\n  \u003cimg alt='webpage' src=\"web.png?raw=true\" width=\"600px\"/\u003e\n  \u003cfigure\u003e\n\u003c/div\u003e\n\n# Disclaimer  / 免责声明\nWe do not hold any responsibility for any illegal usage of the codebase. Please refer to your local laws about DMCA and other related laws.\n我们不对代码库的任何非法使用承担任何责任. 请参阅您当地关于 DMCA (数字千年法案) 和其他相关法律法规.\n\n\n## Features\n- `srt` file for subtitle was supported\n- mutiple speaker was supported in finetune and inference by `srt`\n- huge comfyui custom nodes can merge in xtts\n\n## How to use\nmake sure `ffmpeg` is worked in your commandline\nfor Linux\n```\napt update\napt install ffmpeg\n```\nfor Windows,you can install `ffmpeg` by [WingetUI](https://github.com/marticliment/WingetUI) automatically\n\nthen!\n```\ngit clone https://github.com/AIFSH/ComfyUI-XTTS.git\ncd ComfyUI-XTTS\npip install -r requirements.txt\n```\n`weights` will be downloaded from huggingface automatically! if you in china,make sure your internet attach the huggingface\nor if you still struggle with huggingface, you may try follow [hf-mirror](https://hf-mirror.com/) to config your env.\n\n或者下载[权重文件](https://pan.quark.cn/s/43917b8b8572)解压后把`pretrained_models`整个文件夹放进`ComfyUI-XTTS`目录\n\n## Tutorial\n[Demo](https://www.bilibili.com/video/BV1Wt421u7tu)\n\n## Params\n\n- `temperature`: The softmax temperature of the autoregressive model. Defaults to 0.65.\n\n- `length_penalty`: A length penalty applied to the autoregressive decoder. Higher settings causes the model to produce more terse outputs. Defaults to 1.0.\n\n- `repetition_penalty`: A penalty that prevents the autoregressive decoder from repeating itself during decoding. Can be used to reduce the incidence of long silences or “uhhhhhhs”, etc. Defaults to 2.0.\n\n- `top_k`: Lower values mean the decoder produces more “likely” (aka boring) outputs. Defaults to 50.\n\n- `top_p`: Lower values mean the decoder produces more “likely” (aka boring) outputs. Defaults to 0.8.\n\n- `speed`: The speed rate of the generated audio. Defaults to 1.0. (can produce artifacts if far from 1.0)\n\n\n## WeChat Group \u0026\u0026 Donate\n\u003cdiv\u003e\n  \u003cfigure\u003e\n  \u003cimg alt='Wechat' src=\"wechat.jpg?raw=true\" width=\"300px\"/\u003e\n  \u003cimg alt='donate' src=\"donate.jpg?raw=true\" width=\"300px\"/\u003e\n  \u003cfigure\u003e\n\u003c/div\u003e\n\n## Thanks\n[coqui-ai/TTS](https://github.com/coqui-ai/TTS.git)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faifsh%2Fcomfyui-xtts","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faifsh%2Fcomfyui-xtts","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faifsh%2Fcomfyui-xtts/lists"}