users of at&t natural voices

Category: Geeks r Us

Post 1 by Polka dots and Moonbeams (I've now got the bronze prolific poster award! now going for the silver award!) on Tuesday, 17-Mar-2009 22:25:32

Could you share with us what you think of these voices? What kind of memory do they use? Do they work well with screen readers?

I like how Chrystel sounds on the demo, but I cannot speed her up via the demo. I'm curious how she does at a faster rate.

Thanks

Post 2 by sjtaylor (I can't call it a day til I enter the zone BBS) on Monday, 30-Mar-2009 21:37:49

They are quite ram intensive and at least 1gb is recommended. They still are quite passable at faster speeds.
Cheers

Post 3 by Big Pawed Bear (letting his paws be his guide.) on Tuesday, 31-Mar-2009 1:51:26

agreed with sjtailor here, ram intensive, but workth the ram.

Post 4 by Polka dots and Moonbeams (I've now got the bronze prolific poster award! now going for the silver award!) on Tuesday, 31-Mar-2009 22:10:57

What alternatives do you suggest? Something with a small footprint?

Post 5 by BryanP22 (Novice theriminist) on Sunday, 05-Apr-2009 16:16:23

I personally like the NeoSpeech voices or many of the ScanSoft voices, which can be bought from Nextup.com and possibly other places as well. Only problem is that to buy from Nexup you have to be a registered user of their Text Aloud program or the voices won't install. The only exceptions are the aforementioned NeoSpeech voices. The NeoSpeech voices sound, to me at least, more natural than the so-called Natural Voices. This is quite the irony since the NeoSpeech voices are totally synthetic whereas the Natural Voices are based on actual recorded human speech. The problem you run into with that is that when the voice comes across a word that's not in its dictionary it really mangles it. And you'd be surprised how many common words that can include.

Post 6 by Big Pawed Bear (letting his paws be his guide.) on Sunday, 05-Apr-2009 18:18:34

try akapella voices too from nextup, they are pretty good also.

Post 7 by KC8PNL (The best criticism of the bad is the practice of the better.) on Tuesday, 07-Apr-2009 5:26:22

Here's what I use. For things I want to read, like the few times when I've had to use speech for textbooks and what not, I slow down the ATNT voices and they work fine. I don't think they sound all that weel when sped up, so I use eloquince for that. Neospeech Kate sounds alright to a point when sped up, but begins to be distorted when sped up too much.

Post 8 by motifated (I've now got the silver prolific poster award! wahoo!) on Tuesday, 07-Apr-2009 10:09:22

If you slow Neospeech down to a very slow rate of speed, they sound very drunk. If you find yourself with way too much time on your hands, try typing in a string of profanity, and you'll think you've run into a street person on something.

Lou

Post 9 by Polka dots and Moonbeams (I've now got the bronze prolific poster award! now going for the silver award!) on Tuesday, 07-Apr-2009 13:34:02

How about the
Cepstral voices? I think I spelled that correctly. Are they a small footprint, use little ram?

Post 10 by synthesizer101 (I just keep on posting!) on Thursday, 18-Nov-2010 18:54:09

They sound like they... well... have had things done to them. For example, Amy is blowing away in the wind, Laurence is mentally impaired, and david's trying to sound like a robot. Also, neospeech is based on recordings of human speech. The engines just use different algorithms for concatination of the phones and diphones in the databases. Neospeech's is less intensive, and doesn't take too much space, while at and t uses a more ram-intensive algorithm. I recommend them for a natural voice that is ok in responsibility, but use sapi4 whenever possible, not sapi5. By the way, I have a copy of Mike I can give you. If anyone wants, please pm me. I don't know whether or not it'll fit on my dropbox, but... we'll see if someone wants it, won't we?

Post 11 by BryanP22 (Novice theriminist) on Thursday, 18-Nov-2010 20:47:36

Isn't that illegal?

Post 12 by synthesizer101 (I just keep on posting!) on Friday, 19-Nov-2010 17:50:09

Ok, then I'll throw out this CD. I didn't install it, and I can't get the actual disc to someone. I was just suggesting if someone wanted the files I could send them over the internet. Better not break any laws.
The reason, by the way, that I didn't install it is that I use the real speak direct voices for JAWS. That, and the supposedly illegal eloquence on NVDA when I goout.

Post 13 by synthesizer101 (I just keep on posting!) on Friday, 19-Nov-2010 17:51:03

Oh, and I used to have a copy on my old computer, that's how I know how well it works.

Post 14 by synthesizer101 (I just keep on posting!) on Sunday, 21-Nov-2010 18:19:10

Ok, I have found someone to give the CD to, offer closed.