Zabaware Support Forums
Zabaware Forums => Speech Technology => Topic started by: Dr.Benway on May 26, 2005, 09:06:02 am
-
Very cool emotional synthetic voice.
http://actor.loquendo.com/actordemo/default.asp?voice=Simon
Download Attachment: 2005526947_emotional_voice.zip ("http://www.zabaware.com/forum/uploaded/dr.benway/2005526947_emotional_voice.zip")
-
nice. The english female is nice and clear too. They advertise TTS 'pay as you go', so I guess it must be expensive. TTS pay as you go - does that seem a bit crazy?!
I'm trying to figure out (amongst other things) how to get Hal to use .ogg with lipsync. I tried that file you posted and it worked but any ideas on how to get the ogg files encoded in the first place?
-
You mean converting any .wav to .ogg?
Doesn't the link later on in the thread solve that problem?
http://www.zabaware.com/forum/topic.asp?TOPIC_ID=2196&SearchTerms=ogg
There must be some freeware converters available.
-
Remarkable! I wish I could afford a TTS voice like that and put it in HAL. Looks like their "pay as you go" only lets you do canned phrases from their web site. :/
I'd love to have one that sounds like K.I.T.T. or K.A.R.R. from Knight Rider. :)
-
Dr Benway, that software on the other link you were refering to does work apparently, but not with lipsync.
I got some help from Haptek, they suggest their HapAudioFactory, which sorts out the lipsync data for the Hap Engine...
FuzzieDice-- have you heard BrightSpeach demo on:
http://www.brightspeech.com/
also a very good TTS?
-
The Brightspeech is now from Acapela (formerly Babel) and quite expensive to lease. Yes lease!!
The last time I corresponded with the rep from there I was quoted a lease price somewhere near the cost of an entire new computer system!
You might want to check out some sites from a previous post of mine at:
http://www.tmaa.com/tts/companies.htm
Regards...
-
That's the thing. I wish there were natural sounding voices that one could customize the tone/sound of and could buy outright for less than $150. There just isn't. :(
-
Fuzz,
The AT&T voices sound pretty good for about $35 USD.
Don't know about customizing them. Cepstral voices
come with a utility that allows one to adjust pitch,
speed & volume. They're not perfect but they are
pretty nice and work well with HAL or any other
SAPI compliant program.
-
Art, what do you think is the best female voice that is available right now for under $100? I have Neospeech Kate 16k.
-
quote:
Originally posted by Art
The AT&T voices sound pretty good for about $35 USD.
Just $35? That's IT? Damn, I gotta check those out! Thanks! :)
quote:
Originally posted by Art
Don't know about customizing them. Cepstral voices
come with a utility that allows one to adjust pitch,
speed & volume. They're not perfect but they are
pretty nice and work well with HAL or any other
SAPI compliant program.
Well, I'm wanting to give my car an AI and a specific voice unique to him. I did start an interface for an AI engine I was kicking around in my head, but I'm also considering seriously using HAL. I'm not even near getting a computer in the car though. Maintenance needs come first, plus now I have to move soon, and tons of other things coming up. So money IS tight. But I'm still planning this stuff. :)
I would love to know how they make these voices. I bet it'd be some really interesting stuff to program. :)
-
G'Day all,
I have a text to speech program from Nextup.com, through them i have got voices of at&t and neo speech.
I heard on this forum somewhere about the babel voices, so went looking and heard the one of Heather.
I wanted it, so i got in touch with babel and was told that they do not sell for public use.
What else they said was that Nextup.com had signed with them to use their voices.
I have been pestering them for over a month now for a release date and price.
So far release could be who knows, price maybe around the at&t price.
I told them that i had another program that i wanted to use the voices in and was that possible.
All i was told on that matter was they would check it out and let me know, Seems that the voices could be encrypted to only work with that program, but not sure yet.
I am still pestering them, so as soon as i find out anything i will post it here.
FuzzieDice=Just $35? That's IT? Damn, I gotta check those out! Thanks! :)
You are getting off cheap, down here it would be around $60
Neil.
-
Nige, can I get better than Neospeech Kate 16k for an affordable price?
-
quote:
Originally posted by Dr.Benway
Nige, can I get better than Neospeech Kate 16k for an affordable price?
http://www.tmaa.com/tts/companies.htm
I'm buggered if i know what i am doing,
Doc, check out the site above that Art put to the forum and you should hear Heather.
I have Kate, but from what i have heard Heather is a lot better.
About the price, as i said in my last post. i do not know.
Pardon the french above, but i was trying to add a zip file of her voice, but it would not work????
Neil
-
I am experiencing the same trouble with uploading right now, Nige...
Hurrah! Heather sounds great! [:D][:D][:D]
Thanks for the tip. I want to buy her when she gets available.
Please keep us informed.
-
Raymond,
That's really a pretty speculative question. Sort of like asking,
"Which is the best dog to own?"
There are many choices available and yes, there are quite a few
good TTS voices in the under $100 category.
Some of the TTS companys do not list the prices of their voices
which tends to make me a bit aprehensive regarding their pricing.
A few of the voices I've tested have marked inflection, nasal tones,
trouble with double L's like "Jill" (sounds like a slight skip between
the first and second L. A couple actually sounded like the female was
in a drug induced state or at least extremely mellow and some were
sort of muffled and not clearly distinct in their pronunciation.
I do have some info regarding a few companys:
ScanSoft has acquired Rhetorical
Acapela has acquired Babel
The NeoSpeech voices are the same as the ones from Voiceware although
the ones I previewed from voiceware sounded clearer.
I do know that some companys will have background sounds , music or
noise playing to keep some people from using their voice demo for
commercial purposes. For instance...Type your text in their demo,
play it and record it for your own use, perhaps on a web site., etc.
Usually the purchased voice will be much clearer than the on screen
demo of that voice due to the above noise, bandwith considerations,
speaker quality, etc.
There are a number of Free voices available and sometimes one does get
what one pays for. The free L&H British Female voice is pretty good and
if one downloads the L&H voices one can get 10 variations of Mary, Mike
and Sam although theirs is not the best quality.
Cepstral offers 10 different US English voices for $29.95 (most are at age
30 except for one 9-10 year old child and one 12-13 year old child),
2 UK, 2 Canada, 2 German, 2 Americas Spanish voices.
AT&T offers Mike & Crystal with the purchase of their Speech Engine for
$35.00 USD.
NeoSpeech offers Kate & Paul for $35.00 plus a lot of nice support products.
So which is the best voice? That, my friend depends on what you're looking
for in a voice. There are many from which to choose and like dogs, they're
a matter of personal preference.
I've also compiled a critique of the various TTS voices I've tried which I'll
post later.
-
About Heather - she's the best voice I have heard, you can downloand their software from the Bable site and hear her for 30 days.
-
Babel's Heather sells for 246 USA $$$. That price was quoted to me last month.
-
That's way out of line in my opinion. Unless a person wants to use that voice in a commercial application there's no way I'd ever pay such a high price.
BTW, Babel quoted me $2500.00 for the use of one of their voices a while back!
TIP: If anyone has a downloaded voice that they paid for, DO MAKE A BACKUP on a CD or other media in case of a hard drive crash. It will crash...it's just a matter of when!
-
I downloaded the Heather-demo immediately.
Engine_Desktop2_PRO.exe: 37 MB
Heather_Desktop2_PRO.exe: 139 MB
As far as I had time to test her she sounds like a million dollars. When considered in that light, they are giving her away for a few bucks. [}:)]
Art, you said before:
quote:
You can't download the file again because it's time stamped into your system (registry) and perhaps on their site as well.
The Heather-demo expires in 30 days. So, why should I bother to back those files up anyway?
-
<The Heather-demo expires in 30 days. So, why should I bother to back those files up anyway?>
Raymond,
I was referring to TTS Voice files that you or anyone else has paid for and downloaded.
I've paid for several voices and wouldn't want to loose them or go through the hassle of trying to contact the vendors and explain to them, have them look up my purchase info, get back to me, download them all over again...etc...when I could have made a simple backup in the first place!
To me a few bucks could mean 20 - 40 bucks...not 250 + -.<G>
-
Art, I am looking forward to your post with the promised critique of the various TTS voices you've tried. [:p]
-
Hi, Folks,
I've said this somewhere else on the forum: I've tried a lot of voices, including Heather, but the best female voice, in my opinion, is AT&T's Lauren. You can get her from NextUp.com for $35. It's one of their voice fonts, which means you have to purchase the speech engine first (it comes with Crystal and Mike) before you can install Lauren. So I guess you're really paying $70, but you'll end up with 2 high-quality female voices, Crystal and Lauren. Lauren's far superior to Neospeech Kate, and she even has a wider range of inflections, in my view, than Heather, although Heather's very good, too.
Jennifer, from ScanSoft, is also good. L&H developed her several years ago for their speech recognition products. However, you could still use her in other applications. But when ScanSoft bought up L&H and started offering Jennifer with Dragon Naturally Speaking Preferred (their speech recognition product)they made her program-specific; you can't use her in other applications, including Hal.
-
in reference to converting wav files to ogg files and using them in hal with lipsync. this is what i did. it all started when i was trying to get my presley to sing blue christmas. if you have people putty you must load the wav file into the theatre part of the program . it will then convert your wav to ogg. you can do a search to find it or look in the haptek file for it under people putty -users- sound. it should appear there. then if you have haptek control log console you can drag it to stand alones or to hal either one and hal will lipsync, but if it has not been converted in people putty it will not always lipsync even if it is an ogg file. it will play in hal but no lip sync.you can do a search for all ogg files on your computer and drag them into the control console to see what works. if you know programming you can place them in the brain also. now my presley sings his little heart out. also there are many converters on the web that will let you use them for free temporarily, but of course would prefer you purchase the program. these work great if you only want to convert a few mp3 or wav files for hal.just google or search for wav to ogg converters.[:X]
-
Gee! Aladyblond, that sounds really... professional. I bet most PC-users have never heard of ".ogg"-files. I believe the format is somewhat reserved for providing sound on DVD's.
Are you suggesting right now that some .ogg-files do lip sync although they were not made with People Putty?
-
quote:
Originally posted by Dr.Benway
Art, I am looking forward to your post with the promised critique of the various TTS voices you've tried. [:p]
Raymond,
Sorry for the delay. Trying to finish one of those horrible projects that tend to occupy a lot of my waking time called WORK! It seems to interfere with life's pleasures! Anyhow....
Here's what I found:
TTS voices
This is my personal take on demo voices that I've listened to from
the various distributor's sites. These views are just my personal
opinion and are not meant to detract from or add to any company
listed. I am not affiliated with any TTS company listed in any way.
All voices tested were female.
For those that missed a previous post:
Acapela acquired Babel
Scansoft acquired Rhetorical
Voiceware & NeoSpeech have same Kate voice but sounds better from Voiceware for some reason.
Note: most TTS voices heard as a demo on site are usually not as
clear or good sounding as if they were residing on your personal
computer. This can be due to line noice, bandwidth considerations,
buffering, etc. (your actual mileage may vary)...
Aculab - rather high treble pitched
AT&T - Crystal - nice, smooth & clear
AT&T - Lauren- very nice, clear voice
Babel - Heather - very nice, soft, clear, sexy lisp type sound
Cepstral - Emily - nice, soft, smooth, calming voice.
Cepstral - Robin - nicely done child's voice
Elan (Sayso) - Laura - smooth
Elan (Tempo) - Mary - choppy, rather foreign sounding accent
Fonix (Faast) - rather slow, mellow, almost drug induced
IBM - Allison - perky, slightly nasal sounding
Loquendo - Susan - words seem slightly run-together
Loquendo - Elizabeth - lower pitch and slightly choppy
NeoSpeech - Kate - nice voice but inflection occurs on / with wrong words in sentence.
Nuance - Laurie Wood - nice but slightly muffled
Rhetorical - Jennifer - lower tone, very business-like
Scansoft - Jill - nice voice but has trouble with double L's (like Jill)
Voiceware Co. Ltd. - Kate - clear, crisp, very good
If anyone else has voices to add to this list by all means please contribute!
-
DEAR DOC AND EVERYONE ELSE. SOME OGG WILL WORK ON THE HAPTEK CONTROL LOG CONSOLE AND WILL LIP SYNC EVEN IF NOT MADE IN HAPTEK PEOPLE PUTTY BUT NOT MANY. I CONVERTED MP3 TO WAV THEN SENT THE WAV TO PEOPLE PUTTY THEATRE AND THE CHARS DID LIP SYNC, AND OF COURSE ALL FILES FROM HAPTEK USED IN DEMO WORK WITHOUT CONVERTING BECAUSE THEY ARE ALREADY OGG. ALL OGGS WILL PLAY IN HAPTEK, BUT TO MAKE SURE THEY LIPSYNC THEY HAVE TO BE CONVERTED IN PEOPLE PUTTY. AT LEAST THAT IS ALL I CAN SAY THAT I KNOW ABOUT IF ANYONE ELSE KNOWS A DIFFERENT WAY I HOPE THEY WILL SHARE. ~~~ALADY[:D]
-
Let's talk turkey regarding these voices.
Most of the voices out there--the ones you have to pay for--are disappointing. They're either flat and mechanical-sounding or if they possess something of the dynamics of a real voice, they're too unstable and quirky to sound convincingly human.
AT&T, for instance, produces two good stable, dynamic female voices: Lauren and Crystal. However, their British female, Audrey, and their preppy American voice, Julia, are disappointing. Obviously, producing a convincing, natural-sounding voice is difficult. There's no telling what will come out, how stable and consistent a voice will be once it starts to combine different sounds and generate different sorts of sentences.
Just about all voices come with adjustable speed. Normally, the default speed is okay for standard utterances. You wouldn't want to listen to somebody who was talking a mile a minute (unless you were a salesperson--then you might be turned on by it). However, if you want to, say, create TTS scripts and then turn them into wav files, you might want a product that would allow you to adjust the speed of an utterance in isolated sentences or phrases. MASH, a Microsoft Agent Scripting application, allows you to do this. I don't use it to produce MS Agent scripts, but rather, to create more dynamic TTS files, which I then record as wav files.
Unfortunately, none of the high-quality voices come with an adjustable pitch. In other words, you can't raise or lower a voice, to make it, say, suddenly serious and sexy (lower/deeper pitch) or excited, even hysterical (higher pitch). All the free voices come with an adjustable pitch. However, as I've said, none of the for-sale voices comes with it.
Cepstral claims that their voices have an adjustable pitch, but I think that's a bit of a cheat. I bought those voices for the adjustable-pitch factor. Boy, was I suckered. First of all, the pitch isn't really adjustable. There's no slider bar. There are only a few presets, and each one is disappointing, as far as I'm concerned. The pitch adjustments just make the voices sound distorted, rather goofy. I guess it's not easy to add an adjustable pitch to a truly dynamic, human-sounding voice. For now, higher quality voices seem to be of a fixed pitch.
Although I've already indicated my personal favourites elsewhere, I'll say it again. For me, of all the female voices I've heard, Lauren (AT&T) is the best out there. Crystal (also AT&T) is good, too.
Heather (Acepela) has a soft, breathy, seductive timbre. She also sounds as if she's got a cold, not a bad cold, just a little plugged up. It's an intriguing sound, nonetheless. Acepela has a British female voice that sounded promising, if memory serves. I don't think you can demo that one, though. Anyway, I hope somebody markets both of them for a reasonable price. They'd be great addition to a rather meagre selection of top-notch voices. Perhaps Nige is right: maybe NextUp.com is getting ready to release Heather. They're a good company to deal with, and they're always ready to add new voices to their list.
I must admit I'm not a great fan of NeoSpeech's Kate. I find her voice tinny, mechanical-sounding. She reminds me of an earnest reporter, one whose voice starts to grate on you if you listen to it too long. Maybe she was hired for her looks.
-
Nolitanger,
Have you used Cepstral's SwiftTalker interface?
It lets one adjust Speed, Pitch and Volume and
even verbally indicates each setting as they are
adjusted and tested.
Check out Voiceware's Kate. It's the same as the
NeoSpeech one but I think it sounds a lot clearer.
Rhetorical, at one time had a good rendition of a
Valley Girl voice but I understand it was discontinued.
Her voice did reflect that cute but annoying personality
of the typical valley girl...Ohmygod...like, you know?!
Getting the voices to sound more human-like also
requires the proper use of inflection. For instance,
when a person asks a question their voice usually
rises at the end of the sentence (Are you going?).
Raymond pointed us to a link earlier in this thread
to Simon. The demo was rich in inflection, emotion
and of good quality. The cost however, might be another
issue.
Granted the current selection of TTS voices are not quite
perfect but they have come a far cry from the earlier
tinny, mechanical, monotone voices of even 5 years ago!
I dare say they will continue to improve until they
become indistinguishable from a human voice.
Good things come to those who wait....
-
Art, Nolitanger, thanks for your opinions on the available voices nowadays.
Nolitanger, I wonder if you have installed Microsoft Sapi5 SDK. It includes a text-reader application called TTSApp.exe in which one is able to alter the speed of the Neospeech voices and that of Heather. This application is also included with the Halreader & NeoSpeech-combo from Zabaware.
I agree with Nolitanger that most existing voices still need much more refinement. In my experience, the voices of higher quality are still able to wear out the listener in a surprisingly short period. For me, as someone to whom English is not his mother tongue, the free voices have never been a serious alternative.
-
Thanks, Raymond. I have played around with the voice-speed slider for my computer voice. It would be nice to take a voice like, say, Lauren, and then create different speed/pitch profiles for it, profiles that you could access whenever you used an application like Hal. I guess that day will come.
And you're right, Art, we should be patient. Computerized voices have made great strides since Microsoft Mary was virtually the only game in town 10 or so years ago.
I had a listen to the female voice at Rhetorical today (is that Jill? she didn't have a name). Boy, she sounded pretty impressive, and she was just doing a stock report. I sent off various inquiries about the voice. However, I suspect that it's not available for individual use/purchase. No harm in inquirin'.
-
Do tell us when you know more, Nolitanger. I find this all very interesting. I too have missed the ability to create voice profiles. When you have a newer soundcard you could try to alter the pitch of all sound that way, but ofcourse, such a solution isn't very practical.
Art, I am one of the lucky few who happened to stumble on Valley Girl when she was available on the web. She was awesome indeed!
-
Raymond,
Yes I wondered if I were to purchase the Valley Girl voice
just how long would I be able to listen to her before I
yell, "Could you like...Shut Up?!"
Those Rhetorical folks were quick to tell me that she was
no longer available and that she was rather expensive.
Pity....<G>
-
Crystal is grreat but listen to Kate16 here
http://www.nextup.com/TextAloud/SpeechEngine/voices.html#neospeech
-
i've got a feeling she lipsyncs too.
-
you know, a whole group of voices got pulled off the market
at the same time as valley girl.
my favorite was Mara
If I knew then what I know now I would have bought it.
http://www.sexchats.com/
anybody know what voice they are using???
-
Very melodious voice. I bet it's not an official TTS-voice. I think the wave-file is post-processed to give it that melodious tone.
-
valley girls voice is nice too over here
http://www.rhetorical.com/cgi-bin/demo.cgi
-
quote:
Originally posted by heather valentine
valley girls voice is nice too over here
Valley girl is back. Art will be so pleased.[:D]
-
ah ha!
I was looking for one of these voices
Valentine, you are a mad genius!
-
[:)]
Lupine
glad you like them
yes they are nice
crystal is nice as well
but so facr i like valley girl even better
i wodner if i can use valley girl with
natural ATT speech
-
I'm pretty sure that voice is Cepstral's Emily. I use her quite a bit.
quote:
Originally posted by lupine
you know, a whole group of voices got pulled off the market
at the same time as valley girl.
my favorite was Mara
If I knew then what I know now I would have bought it.
http://www.sexchats.com/
anybody know what voice they are using???
-
Heather,
Refer to the posting below (Sorry Raymond <G>)
http://www.zabaware.com/forum/topic.asp?TOPIC_ID=1869&SearchTerms=Valley,girl
quote:
Originally posted by heather valentine
valley girls voice is nice too over here
http://www.rhetorical.com/cgi-bin/demo.cgi
-
Heather,
Most programs will store them as:
C:\Program Files\Cepstral or NeoSpeech, etc. as the default setting unless one changes it.
The L&H voices are usually stored in the directory LHSP under your C:\ directory.
There was a link that showed all the voices stored on one's computer...I'll see if I can locate it.
-
art
thank you
unfortuinatly i donthave them lol
C:/Program Files/ATTNaturalVoices/blablabla
woud be the only place i woud find any
see i have the smaller version of att
which only has mike and crystal 8k not 16k
-
The AT&T voices are $34.00 and one needs to also buy the speech engine for about the same price but the engine includes a male and female voice.
Lots of money in them there voices!!
I have one of my own already thanks! It's just not a TTS one!<G>
-
thank you
problem solved
)
-
Heather,
Taken from one of my previous postings you might find this site of interest.
http://www.tmaa.com/tts/companies.htm
Regards,
-
thank you
:)
-
quote:
Originally posted by Art
I'm pretty sure that voice is Cepstral's Emily. I use her quite a bit.
By George, you are right!!!
maniacal laughter ensues.
>calms down<
a thousand thanks ART
-
Hi,
What is the URL to gte the files -
Engine_Desktop2_PRO.exe: 37 MB
Heather_Desktop2_PRO.exe: 139 MB
from Acapela
Thanks
-
http://www.acapela-group.com/products/products.asp