Jayson SmithHere's a demonstration of Richard, one of the two new Blastbay formant-based neural text to speech voices. In this demo, I've deliberately installed the trial version on one of my computers so you get to hear the degraded audio once the one-minute trial period ends. Transcript in alt text.
Andre Louis@jaybird110127 Good AudioMo.
@FreakyFwoof Yeah I didn't use the hashtag since I haven't been participating.
@jaybird110127 No reason not to, if you want to. Nobody has to participate once, twice or even at all.
The Evil Chocolate Cookie@jaybird110127 @FreakyFwoof so getting involved in the middle of the month is perfectly acceptable? What is it anyway? I saw it this year, I saw it last year, and I still don’t understand it one little bit.
@evilcookies98 @jaybird110127 Posting audio in the month of June with the hashtag. That's it. That's all there is to it. You join a group of us that post a lot or a little. The AudioMo account boosts each one that joins the hash tag and posts audio, so it's seen by a group of people that are not necessarily your followers. It's fun.
@jaybird110127 @FreakyFwoof all right! That sounds like fun. I’m totally in.
@evilcookies98 @jaybird110127 Search for the hash tag. You'll find posts from all over the world, all sorts of people, you may even like some of them.
@jaybird110127 @FreakyFwoof this is awesome sauce. Too bad I wasn’t recording the other night when my glasses misidentified one of my audio games as a sex toy. That would’ve totally been worth posting.
@evilcookies98 @jaybird110127 If you look at the hash tag, you'll see all sorts of people joining in. Blind, sighted, it's probably the time when more sighted people post audio than ever before. Just because you didn't post every day this month, no reason stopping you posting even the once and never again if you don't wish to.
@jaybird110127 When the 1-minute trial period expired, it sounded like a rather low quality telephone line, with static and a pretty authentic phone filter thing going on. I've never heard any TTS trial do that before. This synth is very impressive. I hope more people purchase these voices.
Jamie Pauls@jaybird110127 @FreakyFwoof I am seriously considering purchasing. Glad to know tBlastBay is still out there making content. Quite a departure from Q9, but I like it.
@jaybird110127 Why do we need these? Legit, honest question. Why is he selling these, there aren't enough voices out there? What's the benefit of this?
@remixman @jaybird110127 Because, as much as some refuse to admit it, Eloquence has been living on borrowed time for years, and it's only a matter of time before it goes completely belly-up. How long can it keep getting patched, repatched, etc. before it just doesn't work? Dectalk has had a hell of a revival, but it's about as much of a legal grayarea as a fanfic. Besides, if we want any hope of mainstream accessibility in embedded devices - think kitchen appliances...
@jackf723 @jaybird110127 Sure. This is nothing like Eloquence, though, sadly.
@jaybird110127 @remixman It's also the principal of the matter. How long's it been since we've had a speech synthesizer truly built for performance hit the commercial market, much less one entirely developed, end-to-end, by someone with more than two decades of screen-reader use, who has not only r&d but all that lived experience with screen-readers to go off of in the build process? You had Dolphin Apolo/Juno/Orpheus as an example of a screen-reader company developing
@jaybird110127 @remixman their own end-to-end synthesis, and that was about it. Speakout/SoundingBoard worked off of existing end-to-end infrastructure. We almost had speechplayer, but if that used Espeak's phonemizer, it wouldn't be embeddable in commercial devices without opensourcing firmware. With this newly-released speech, we have,, possibly for the first time, a speech synthesizer built for us, by us, that truly has a fair shot at mainstream acceptance.
@remixman @jaybird110127 UEFI, etc. then there needs to be a modern, licensable, significantly lighter-weight tts that has the benefit of being formant-based while baring the good parts of neural synthesis, so that you have a synth that's a Eloquence/Dectalk levels of responsiveness for screen-readers/embedded devices, yet at the same time quite listenable for a general audience.
@jackf723 @remixman @jaybird110127 And just wait until NVDA goes all 64-bit after they end Windows 10 support. Unless somebody really goes the extra mile for it, IBM TTS will no longer be an option.
@sclower @remixman @jaybird110127 And even given someone with enough knowhow to develop a bitbridge, you'd need access to at least some of the Eloquence codebase to make it run well, and even then no one, even from Cerence, has the inclination or will to truly refactor it. And if Assistive Technology ever were a Price is Right/Sale-of-the-Century category, my money is on the guess that licensing costs Aple paid to Cerence would be in the tens of thousands. Lol.