Computers and Technology

Speech synthesizers

Started by hozosch 554 posts last post 1 year ago Page 9 of 28

#161

read it with espeak
nguewnguewnguewnguew! nguernguernguernguerwnguerwnguerwnguerwnguewnguernguewnguerngue! nguebnguexnguexnguezngueqnguequnguequnguenguequnguequngue!
my github: https://github.com/denizsincar29

#163 Edited

Hi,
As the begin I used Scansoft Agata for sapi5. Next, Ivona Ewa, Jacek, Speechplayer, and finally I use espeak wariant sandro.
Sometimes I use Speak II Jan (readboard), vocalizer Ewa Compact, SMP (Syntezator Mowy Polskiej), and Spiker IVO Software.
I read English texts with Polish synthesizers, because I know how a given word is written.

#164

I heard of speech player but I didn't really get what it is.
Is it a version of eSpeak with extra voices?
--
Seva
https://github.com/sevapopov2

#165

it's a klatt based ver of espeak so basicly yes. also you can edit the voice. like the fraims and stuff
Trussville roll: Deep-fried, smoked salmon, crab salad, cream cheese, topped with mango sauce, sweet soy-reduction, green onion. MMMMM

#166

Is it possible to find it now? I mean the new version.
I found a klad voices in eSpeak but also don't get a thing what they are, is it the special version of the voice?
:D
What does it mean klad based then?
--
Seva
https://github.com/sevapopov2

#167

here it is
Trussville roll: Deep-fried, smoked salmon, crab salad, cream cheese, topped with mango sauce, sweet soy-reduction, green onion. MMMMM

#168

Thank you!
Now I understand where these new eSpeak voices come from.
I mean new voices in eSpeak ng that aren't included in NVDA yet.
--
Seva
https://github.com/sevapopov2

#169

.you're wellcome verry mutch
Trussville roll: Deep-fried, smoked salmon, crab salad, cream cheese, topped with mango sauce, sweet soy-reduction, green onion. MMMMM

#170

Yes, speech player is also part of ESpeak NG.

#171

Microsoft Azure have more Microsoft speeches which we can't access.

#172

By the way, did anyone have any experience compiling new espeak ng for windows?
I could do it only on linux.
It would be interesting to compile it for windows to use in nvda.
--
Seva
https://github.com/sevapopov2

#175

Yes, and it's implemented as Klatt 6.

#176

and... these voices will be the part of new NVDA.
Student studentowi wszystko

#178

That's nice.
I listened to these voices in linux, some of them sound really interesting, I don't even know how and who creates them.
I believe that the eSpeak voices now are created by users.
I will be glad if there are also improvements that are connected with languages and different phonems. For example for Spanish.
--
Seva
https://github.com/sevapopov2