I had run across the online demo of the AT&T Natural Voices TTS engine quite awhile ago, but seeing a reference to it in an article today on Slashdot reminded me of how cool it is. You enter text in a text box and choose a voice from a list of thirteen. The list includes five US English, two Latin American Spanish, two French, two German, and two UK English voices, with a near even balance between male and female voices.
After you submit the request, a wav file is generated immediately on the AT&T server and downloaded by your web browser. The quality is really quite good.
While you can, of course, enter English text and have it synthesized by a Spanish, French, or German voice, the text won’t be translated. That would require a little hacking to pipeline the output of Altavista Babel Fish, Google Translate, SYSTRAN, etc. into this form. However, if you were ever wondering how someone from a German, Spanish, or French speaking country might mispronounce a particular English word, here’s your chance to find out.
FYI, the free VoiceXML hosting service at TellMe uses Natural Voices. BeVocal offers a couple options on their hosting service – male and female US English voices, a Spanish female voice from Nuance Vocalizer, and a German female voice from ScanSoft RealSpeak. I think that the US English voices, Jennifer and Mark, are RealSpeak voices.
It turns out that ScanSoft also has a demo page for RealSpeak. ScanSoft/SpeechWorks acquired RealSpeak from Lernout & Hauspie a few years ago after L&H self-destructed. You first pick from 19 different languages, and then from three different sampling frequencies. Assuming you are going to be using the TTS on PSTN phone calls, pick 8 kHz. On the next page, you select a voice (if more than one are offered for the language you chose) and then enter up to 100 characters to be synthesized. Unfortunately, when I clicked the Next button, I got an error message from my web browser that “The connection was refused when attempting to contact demo.lhsl.com”. Perhaps this is a temporary problem, or maybe they no longer support the demo running from that old L&H domain, but they haven’t updated the product pages on the ScanSoft website, yet?
ScanSoft also has a demo page for their premier TTS engine, Speechify. You get to pick from eleven different languages and voices. The text input is limited to 255 characters.
Nuance offers a demo of Vocalizer, but you have to fill out a form. Fortunately, you get immediate access to the demo after submitting the form. The Vocalizer demo includes a mix of eight language and voice combinations. The text you enter is limited to 200 characters.
As an aside, voices for TTS engines are traditionally given a first name. The name is typical of the language, e.g., Tomoko for a Japanese voice, Maarten for a Dutch voice, and Javier for a Spanish voice. The Vocalizer voices have a first name and last name, e.g., the male Australian voice is Josh Donnelly and the female Latin American Spanish voice is Catalina Romero.
If you want to try out more online demos from lots of smaller companies and from research groups and open source projects, check out this page at the University of Texas. It’s a pretty comprehensive list. There is also a good links page at the Oregon School of Science & Engineering website that provides links to a lot of TTS research projects.
Probably the best known open source TTS engine is Festival, from the University of Edinburgh. You can try an online demo of Festival at a site hosted by Carnegie-Mellon University. There are a combination of twelve voices and languages. The biggest differentiator is the male Scottish voice. Unfortunately, the quality of the Festival synthesized voices is a big step down from what ScanSoft, Nuance, and AT&T have to offer. If you used a Macintosh in the mid-80’s, you will have flashbacks to the talking moose. I would say that the output from the Festival engine is on par with the second or third tier TTS players, like Microsoft.
good!
Thank u for this message
I was searching for High quality text-to-speech software.
Your links r exellents
Pingback: WombatNation » SpeechTEK West 2006 Day 1
GOOD
hey your really cool
i was looking for a great text to speech website and you did not help me find it at all… thanks alot
hey great. I’m sarcastic! Isn’t that great?
you guys are dumb! so stupid!
This is the way I live
Lilâ?? Boy still pushinâ?? big wheels
I stack my money, lay low, and chill
Donâ??t need to work hard thatâ??s the way I feel, I feel, I
This is the way I live
Lilâ?? Boy still pushinâ?? big wheels
I stack my money, lay low, and chill
Donâ??t need to work hard thatâ??s the way I feel, I feel, I
This is the way I live
Six months later now weâ??re big dog status
Name elevated but I still act average
Rockinâ?? shows in Dallas, ball like I play for the Mavericks
West Bank rapper and Iâ??m one of the baddest
French Rivera spot and I am getting in shape man
I think Iâ??m Super M-a-n without a cape man
Ridinâ?? all day hustlinâ??, all for the cake man
Iâ??m a Benjamin stack one inch taller than Great Danes
First they made cheap Ray-Ban like a felon
Iâ??m growinâ?? up now spittinâ?? hotter than Mount Hellens
Iâ??m a steal every girl ever gonâ?? to fly
Iâ??m a young little dude, stay runninâ?? from cops
Emerald Row is the place where I got my props
People love me in the hood they donâ??t want me to stop
So uhh, thatâ??s the only way I know how to rock
And Iâ??m a stay rappers like wonâ??t stop â??til I drop
This is the way I live!
Lilâ?? Boy still pushinâ?? big wheels
I stack my money, lay low, and chill
Donâ??t need to work hard thatâ??s the way I feel, I feel, I
This is the way I live
Lilâ?? Boy still pushinâ?? big wheels
I stack my money, lay low, and chill
Donâ??t need to work hard thatâ??s the way I feel, I feel, I
This is the way I live
I Iâ??s Baby Boy and I done it again
Iâ??m ridinâ?? fly with D-Wizzle in â??cedes Benz
Twenty two wanna ride with the ladies then
Red Bull, Grey Goose, now the ladies bent
Now we go and do a thing under a shady tent
And they donâ??t question what I say â??cause Iâ??m a ladies pimp
See this little one right here this fellow got stripes
And I is represent, my rail room for life
Money in my pocket but I still act trife
While I in the club they say the parlor ainâ??t right
Look Iâ??m–doing great thatâ??s the way I feel
Hustlinâ?? hard all day thatâ??s the way I live
This is the way I live
Lilâ?? Boy still pushinâ?? big wheels
I stack my money, lay low, and chill
Donâ??t need to work hard thatâ??s the way I feel, I feel, I
This is the way I live
Lilâ?? Boy still pushinâ?? big wheels
I stack my money, lay low, and chill
Donâ??t need to work hard thatâ??s the way I feel, I feel, I
This is the way I live
This the two-seat rider with the ketchup inside
Red pepper paint must believe my ish ride
They pause like stop signs when they rollinâ?? up
Causeâ?? when the doors open up, they open UP
Iâ??m Lamboinâ?? it I was stashed, off stage Iâ??m throwinâ?? it
Cause they say Iâ??m like Katrina with money, I blow the shhhh
Real been gravy, three years out of the eighties
Solos, shaboâ??s valley animals played it
Commodores mirages, not the Nike hirages
It cost 250 on up to put your foot inside this
Yâ??all was wearing rocks that was my time to shine
Donâ??t give me viesels yâ??all thinkinâ?? this McDonalds size
I been fly I I I I I I I I from the crib to the ri I I I I I de
Fifty-Four inch screens 26 inches from the ceiling dude
The plasma look like a projector up in the livinâ?? room homie!
This…. is… the… way I live!
Lilâ?? Boy still pushinâ?? big wheels
I stack my money, lay low, and chill
Donâ??t need to work hard thatâ??s the way I feel, I feel, I
This is the way I live
Lilâ?? Boy still pushinâ?? big wheels
I stack my money, lay low, and chill
Donâ??t need to work hard thatâ??s the way I feel, I feel, I
This is the way I live
wait, what is this?
yea what is this
You should check out YAKiToMe! (http://www.yakitome.com). It uses the highest-quality text to speech voices to automatically turn any electronic text into an audio book podcast that you can download and share. It has none of the limitations of the sites listed in the above article. It also support multiple languages, has male and female readers, lets you control speed and pronunciation, and has a growing library of free podcasts ready to download. I use it all the time to listen to books and homework and it’s great.