A sound cloning tool with a web interface, using your voice or any sound to record audio / 一个带web界面的声音克隆工具,使用你的音色或任意声音来录制音频
百度网盘下载链接: https://pan.baidu.com/s/1YpvBYmKcogi1eA04FNjU3Q?pwd=9sye
GitHub download: https://github.com/jianchang512/clone-voice/releases/download/v0.907/clone-voice-v0.907.7z
升级包下载to0.904/直接覆盖app.exe即可:https://github.com/jianchang512/clone-voice/releases/download/v0.907/app.exe
为减小体积,主文件内不含模型,模型请单独下载,点击去下载模型
本项目所用模型为coqui.ai出品的xtts_v2,模型开源协议为Coqui Public Model License 1.0.0,使用本项目请遵循该协议,协议全文见 https://coqui.ai/cpml.txt
The model used in this project is xtts_v2 produced by coqui.ai, and the model open source license is Coqui Public Model License 1.0.0 , please follow this agreement when using this project. The full text of the agreement can be found at https://coqui.ai/cpml.txt
百度网盘下载链接: https://pan.baidu.com/s/16xPodHMqXB7t8VVqnHouqg?pwd=qtai
GitHub download: https://github.com/jianchang512/clone-voice/releases/download/v0.901/clone-voice-v0.901.7z
如果已有旧版软件,可仅下载该升级包,将解压后的app.exe和文件夹复制到原软件目录下覆盖即可
GitHub download:https://github.com/jianchang512/clone-voice/releases/download/v0.901/PatchUpdate-to-v0.901.7z
为减小体积,主文件内不含模型,模型请单独下载,点击去下载模型
本项目所用模型为coqui.ai出品的xtts_v2,模型开源协议为Coqui Public Model License 1.0.0,使用本项目请遵循该协议,协议全文见 https://coqui.ai/cpml.txt
The model used in this project is xtts_v2 produced by coqui.ai, and the model open source license is Coqui Public Model License 1.0.0 , please follow this agreement when using this project. The full text of the agreement can be found at https://coqui.ai/cpml.txt
百度网盘下载链接: https://pan.baidu.com/s/1YliZiPMXtSFSHI9vk9uajQ?pwd=racj
GitHub download: https://github.com/jianchang512/clone-voice/releases/download/v0.888/clone-voice-v0.888.7z
如果已有旧版软件,可仅下载该升级包,将解压后的app.exe和文件夹复制到原软件目录下覆盖即可
GitHub download:https://github.com/jianchang512/clone-voice/releases/download/v0.888/PatchUpdateTo--0.888.7z
为减小体积,主文件内不含模型,模型请单独下载。
百度网盘下载链接: https://pan.baidu.com/s/1-GSGzOfymUSCx4MNaNQACg?pwd=kyuk GitHub download:https://github.com/jianchang512/clone-voice/releases/download/v0.8.8.6/clone-voice-v0.8.8.6.7z
为减小体积,主文件内不含模型,模型请单独下载。
修复日语时错误 #40
github.com:https://github.com/jianchang512/clone-voice/releases/download/v0.8.8.5/clone-voice-v0.8.8.5.7z 百度网盘: https://pan.baidu.com/s/154kt8eNSuftsbiWaDA3yQw?pwd=wjp2
为减小体积,主文件内不含模型,模型请单独下载,模型3G,github无法上传。该项目所用模型均源于 coqui-ai 模型协议为CPML只可用于学习研究,不可商用。
百度网盘下载链接: https://pan.baidu.com/s/1CBnPmNElB3LHG7r_McAIwQ?pwd=61jc
Google driver download link https://drive.google.com/file/d/1j8YZgbWDFCm5cWVsbCcL-P7HvGoxrzCH/view?usp=drive_link
模型下载后解压到软件目录下的 tts 文件夹内,解压后如图
fixed #40
github.com download link:https://github.com/jianchang512/clone-voice/releases/download/v0.8.8.5/clone-voice-v0.8.8.5.7z
Models from https://github.com/coqui-ai/TTS ,license is CPML only use for research and learning,To reduce volume, the main file does not contain the model. Please download the model separately as it cannot be uploaded to 3G or GitHub
Google driver download link https://drive.google.com/file/d/1j8YZgbWDFCm5cWVsbCcL-P7HvGoxrzCH/view?usp=drive_link
After downloading the model, unzip it to the tts folder in the software directory, as shown in the figure
修复bug,调整模型缺失提示
百度网盘下载: https://pan.baidu.com/s/1kh1eSRvmf86hPAliDWe5lw?pwd=pstv 提取码: pstv
从github.com下载/点击Assets内clone-voice-0.8.2.7z 或此链接:https://github.com/jianchang512/clone-voice/releases/download/v0.8.2/clone-voice-v0.8.2.7z
为减小体积,主文件内不含模型,模型请单独百度网盘下载,模型3G,github无法上传
模型下载链接: https://pan.baidu.com/s/1CBnPmNElB3LHG7r_McAIwQ?pwd=61jc 提取码: 61jc
模型下载后解压到软件目录下的 tts 文件夹内,解压后如图
下载解压到某个英文目录下(路径不要有空格),然后双击 start.bat 或 app.exe ,等待黑窗口里显示 "http://127.0.0.1:9988" 并自动在浏览器里打开该地址,就可使用了。
链接: https://pan.baidu.com/s/1u2IC_7cwZ5YtzUgplbK5SA?pwd=dtd9 提取码: dtd9
压缩包已包含所有模型,体积较大,分成2个压缩卷下载,下载后放在同一文件夹内,全部选中解压。
更新模型
该项目所用模型均源于 https://github.com/coqui-ai/TTS ,模型协议为CPML只可用于学习研究,不可商用
下载解压到某个英文目录下(路径不要有空格),然后双击 start.bat 或 app.exe ,等待黑窗口里显示 "http://127.0.0.1:9988" 并自动在浏览器里打开该地址,就可使用了。
链接: https://pan.baidu.com/s/1DktcZyxDMVmZu5_LsHDFqw?pwd=si6w 提取码: si6w
压缩包已包含所有模型,体积较大,分成2个压缩卷下载,下载后放在同一文件夹内,全部选中解压。
如果提示 连接 github.com 失败,请下载此文件,解压到 tts_cache
文件夹内,如果不存在 tts_cache
文件夹,先创建,然后在内解压
为减小编译包体积,语音->语音(speech-to-speech)模型未包含在内,需要单独下载后放到项目根目录下的tts里,即和 app.exe 同目录的 tts 文件夹里,然后 "解压到当前文件夹" 模型下载地址
下载解压到某个英文目录下(路径不要有空格),然后双击 start.bat 或 app.exe ,等待黑窗口里显示 "http://127.0.0.1:9988" 并自动在浏览器里打开该地址,就可使用了。
链接: https://pan.baidu.com/s/14KVqP38oREakv_l_7TQcmQ?pwd=iver 提取码: iver
为减小编译包体积,语音->语音(speech-to-speech)模型未包含在内,需要单独下载后放到项目根目录下的tts里,即和 app.exe 同目录的 tts 文件夹里,然后 "解压到当前文件夹" 模型下载地址
下载解压到某个英文目录下(路径不要有空格),然后双击 start.bat 或 app.exe ,等待黑窗口里显示 "http://127.0.0.1:9988" 并自动在浏览器里打开该地址,就可使用了。
链接: https://pan.baidu.com/s/1Hvnb8270xJenUKpFUq-ZaQ?pwd=7ikb 提取码: 7ikb