I've always wondered if there is something like this for the voice of Majel Barrett-Roddenberry (Computer). I know her voice was recorder phonetically before she died (<a href="https://io9.gizmodo.com/the-voice-of-star-treks-computers-could-be-coming-to-bo-1786251988" rel="nofollow">https://io9.gizmodo.com/the-voice-of-star-treks-computers-co...</a>), but I don't think there's public access to that.<p>Perhaps transfer learning could be used to copy the style, using something like SV2TTS.
Very cool effort, but I think it sounds more like Daleks from Dr. Who.<p><a href="https://www.youtube.com/watch?v=YQLbwOGT8eM" rel="nofollow">https://www.youtube.com/watch?v=YQLbwOGT8eM</a>
This is cool but I'm curious why it sounds so much worse than the built in speech to text API<p><a href="http://greggman.github.io/fanfictionreader/" rel="nofollow">http://greggman.github.io/fanfictionreader/</a><p>Which voices are available are browser and OS dependent and there's no "borg" voice anymore. There used to be several alien and or non human voices but Apple removed them from the OS and most browsers just call the OS's text to speech API<p>--correction--<p>You need to go into the VoiceOver Utilities and add all the novalaty voices back in<p><a href="https://recordit.co/ZGgw9MhepW" rel="nofollow">https://recordit.co/ZGgw9MhepW</a>
Can this be modified to include the original voices from the 1998 <i>Microsoft Sam TTS Generator</i>, or is that voice technology not open-source?<p>ex: <a href="https://tetyys.com/SAPI4/" rel="nofollow">https://tetyys.com/SAPI4/</a>
It would be fun if you could generate a link with a hash of a message so you can send it to your friends and coworkers with a silly message that autoplays.