Welcome to the MacNN Forums.

ginop1 · Oct 4, 2003, 03:51 PM

Reading this forum and various other forums, I see that there will be a new high quality voice added to Panther called Vicki. I am unable to speak due to a stroke at the age of 13 and I use Apple's text to speech to speak with friends over the phone using the Fred voice (and now that I own an iSight, as of last week, it would be nice to use text to speech to communicate with people I video chat with). Needless to say that I am very much interested in Apple's text to speech abilities. I saw that someone wrote that not even Vicki compared to voices that AT&T uses. The person left the URL of the demo to hear the AT&T voices. Another person had a link to a demo of Vicki. They are right, AT&T's voices sound better than Vicki or any of the other text to speech voices that Apple uses. Some were speculating that Vicki's huge file size means that some time down the line that Apple will be upgrading their text to speech abilities either in one of the incremental upgrades of Panther, or maybe it will mean a new iApp.

I would like to hear other people's opinions on where Apple's text to speech abilities, or rather, technology is going.

calumr · Oct 4, 2003, 04:01 PM

One of the interesting things I heard about the TTS in Jaguar (it's probably even better in Panther) is that it changes the way it pronounces parts of words, not just based on the next/previous word, but on the contents of the whole paragraph it is in.

There was a session at the WWDC this year on speech & Mac OS X:

402 - Mac OS X Speech Technologies

This session provides an overview of Speech technologies on Mac OS X and introduces significant enhancements to the quality of Text to Speech. Learn about Cocoa classes that enable quick and easy integration of speech within your application, find out about a new tool enabling the speech synthesizer to copy the emotion and personality of a recorded human voice, and understand what speech functionality you get for free in Mac OS X and what you need to do to deliver the best Speech experience for users--a key component in fulfilling accessibility requirements.

I doubt that TTS will stagnate, but is there anything else they can do apart from improve the (already good) quality of the voices?

Developer · Oct 4, 2003, 04:14 PM

Originally posted by calumr:
Is there anything else they can do apart from improve the (already good) quality of the voices?

They could make voices available for other languages for example.

pat++ · Oct 4, 2003, 04:28 PM

Originally posted by Developer:
They could make voices available for other languages for example.

amen to that. same thing for speakable items.

lookmark · Oct 4, 2003, 04:39 PM

Unfortunately high-quality TTS voices like NaturalVoices are currently only available to Windows apps (like http://www.readplease.com/).

There's been lots of rumors of upcoming advanced TTS in OS X (including one leaked, real-looking screenshot of a "Reader" app in progress named iBrary, at least in development) but it looks like it's been nixed, or at least delayed until 10.4.

Gino, if I were you, I'd write to Steve Jobs personally on this (sjobs@apple.com). Be civil and polite, but tell him just what you said in your first post.

ginop1 · Oct 4, 2003, 04:54 PM

lookmark, thank you for the advice. I will go ahead with it. Writing to the man himself certainly couldn't hurt.

Arkham_c · Oct 4, 2003, 07:11 PM

Originally posted by Developer:
They could make voices available for other languages for example.

At one time they had spanish and japanese voices. I don't know what became of them.

Supervince · Oct 4, 2003, 07:13 PM

ginop1 just try Speechissimo

I've found the demo breathtaking, even in french. They havce several language

ginop1 · Oct 4, 2003, 07:30 PM

Supervince, I do know of Speechissimo. What stinks is that you cannot download a demo of the program itself. Hearing a demo via the web is fine, however, I want to know how the program runs on my Macintosh. Will it crash, will I be able to access it fast, are there certain words it cannot pronounce correctly. Those are things you cannot answer with a web demo.

SupahCoolX · Oct 4, 2003, 10:07 PM

According to this article, Apple appears to be working on more accessibility capabilities to OSX. I'm sure it will take a while before these developments really come to fruition, though.

nickm · Oct 4, 2003, 11:44 PM

This isn't too helpful, but I just noticed that Panther/Vicki pronounces "x" as "ex" but "mac os x" as "mack-oh-es-ten". Pretty spiffy.

I think Vicki sounds better than previous Mac voices, but of course doesn't hold a candle to the AT&T voices, which apparently take hundreds of megs of datafiles to define!

Synotic · Oct 5, 2003, 12:45 AM

Originally posted by nickm:
I think Vicki sounds better than previous Mac voices, but of course doesn't hold a candle to the AT&T voices, which apparently take hundreds of megs of datafiles to define!

People always mention AT&T's text to speech, but compared to all other modern text to speech, it's the worst out there (ok, maybe an exaggeration, but it's not definitely not the best). Two of them are Rhetorical's rVoice and Babel's BrightSpeech. Last I checked, BrightSpeech's the best. Unlike the others, it could actually fool you that it was real. It includes French, German, Spanish, Swedish, and U.S. English. The French is excellent (not surprising, seeing as they are a Belgian company). I can't vouch for the other ones, but they sound pretty good. Here's a demo wav if you're interested. Babel also have a product called Babil that includes more languages such as Arabic, Czech, Dutch, Portuguese and Turkish for specialized uses, but it isn't as natural as BrightSpeech. It's still radically better than MacSpeech however.

Lew · Oct 5, 2003, 05:57 AM

Originally posted by nickm:
This isn't too helpful, but I just noticed that Panther/Vicki pronounces "x" as "ex" but "mac os x" as "mack-oh-es-ten". Pretty spiffy.

The Jaguar text-to-speech does that as well

esc · Oct 5, 2003, 06:47 AM

In the TTS world these days there are several packages that someone (Apple or a third party) could have ported and license for $$.

I know one of the folks involved in the AT&T effort (which they thought was going to be highly sought after by everyone, but very few customers materialized). The feeling was that a port to OS X would be straightforward.

The question is really how much of a demand is there for high quality voices on a Mac (enough to justify the high licensing fees and the cost of porting)...

Bouba · Oct 5, 2003, 03:20 PM

Apple's technology on TTS is far more advanced that we all think. Do you remember a couple of years ago, in the superbowl ad with Dave (2001: a space odyssey)??? The computer voice has been generated with TTS technology developped by Apple... The quality is breath taking! I was expecting to see it in Mac OS X but I yet have to see this...