<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40"><head><meta http-equiv=Content-Type content="text/html; charset=us-ascii"><meta name=Generator content="Microsoft Word 14 (filtered medium)"><style><!--
/* Font Definitions */
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0cm;
margin-bottom:.0001pt;
font-size:11.0pt;
font-family:"Calibri","sans-serif";
mso-fareast-language:EN-US;}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:blue;
text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
{mso-style-priority:99;
color:purple;
text-decoration:underline;}
span.EmailStyle17
{mso-style-type:personal-compose;
font-family:"Calibri","sans-serif";
color:windowtext;}
.MsoChpDefault
{mso-style-type:export-only;
font-family:"Calibri","sans-serif";
mso-fareast-language:EN-US;}
@page WordSection1
{size:612.0pt 792.0pt;
margin:3.0cm 2.0cm 3.0cm 2.0cm;}
div.WordSection1
{page:WordSection1;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]--></head><body lang=DA link=blue vlink=purple><div class=WordSection1><p class=MsoNormal>Hi,<o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>This might be a bit off topic for the list, but I thought I’d share it anyway, if anyone schould be interested, so I hope it’s not a problem.<o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>Some months ago, Blake Roberts posted some links on the list to some songs, which was sung by an artificial intelligence recreating a specific human voice, using a technology called SVC.<o:p></o:p></p><p class=MsoNormal>I have recently learned about a program called RVC, which is a better, and easiere to use, version of SVC. The program works by using a voice model to convert an audio file with a speaking, or singing, voice, into sounding like that specific voice. As an example, You have installed a voice model of Frank Sinatra, and record an audio clip of yourself speaking. You then convert the audio clip with RVC, and with Frank Sinatra as the selected voice model. Now, the resulting audio file will have the exact same spoken text as before, but now spoken by Frank Sinatra. The same gos with singing, and it all works across languages.<o:p></o:p></p><p class=MsoNormal>Many voice models are available for download on the internet, of various wellknown singers and actors, created by users of the program. It is possible to make your own model of your own, or some other, voice, but it requires a very powerful computer.<o:p></o:p></p><p class=MsoNormal>The program is most widely used to make cover versions of songs, sung by other singers, sutch as Freddie Mercury singing ”All I want for christmas is you” by Mariah Carey, and I have personally used it a lot for just that.<o:p></o:p></p><p class=MsoNormal>The program is a bit tricky to install, and have a lot of different settings, but it’s fairly easy to use, and doesn’t require any programming knowledge, as was the case with SVC. It is also fully compatible with screen readers, since the interface opens in Google Chrome, as more or less a normal website.<o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>RVC can be downloaded here:<o:p></o:p></p><p class=MsoNormal><a href="https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/RVC-beta.7z">https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/RVC-beta.7z</a><o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>Kind regards:<o:p></o:p></p><p class=MsoNormal>Aksel Christoffersen<o:p></o:p></p></div></body></html>