<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 15 (filtered medium)"><style><!--
/* Font Definitions */
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;}
@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:0in;
font-size:11.0pt;
font-family:"Calibri",sans-serif;}
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;}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;}
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=EN-US link="#0563C1" vlink="#954F72" style='word-wrap:break-word'><div class=WordSection1><p class=MsoNormal>Not sure who would be interested in this, but chat-gpt AI has created a new and original espeak variant... I gave it the following prompts:<o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>note: you may have to press shift enter to insert new lines in multiline edit field if needed. <o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>prompt 1. gather all information about espeak-ng and nv speech player for NVDA, then read the following voice variant file, stop, and wait for further instructions.<o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>variant file contents go here.<o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>after it finnishes its first response, time for prompt 2. <o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>prompt 2. Now based on the contents of the above variant file, create a new original voice variant, include klatt 6, and make it a big improvement which sounds much better than the original glen (insert variant name here), variant.<o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>After prompt2 is completed and you get its output, you paste it into a new variant file, and do some hand editing to remove extra comments, bad formatting and punctuation, changing the case of some letters from upper to lowercase and so on, and any needed info for the variant to work. so yes some human intervention is needed at the end, but it works! chat-gpt can make espeak ng voice variants! <o:p></o:p></p><p class=MsoNormal>It made me a new original variant called aurora. <o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p></div></body></html>