Kenny was a wise man!
 

Guys, first have a read of the post: by our community member Kenny:

Before you wipe your tears of laughter away, and calm your aching stomach, it is really a post of TMO!

But, maybe Kenny was a wise man!:p

Maybe, he is creating his own voice to text software, and has just posted a comment using his dictation!! who knows...

Speaking of that what are the best opensource voice-to-text source codes out there??? It will be great to start a garage project that can bring it out (and rival Google's). Me included.

Lets be Kenny :p

Re: Kenny was a wise man!
 

There is none. Linux has been a pathetic failure with regard to text to speech (oops, speech to text -- both!), and I have seen nothing from the Festival mailing list I have been on for many years to indicate things have changed.

Kenny's message was a horrible one to repost.

Re: Kenny was a wise man!
 

I find it amusing you use such aggressive phrases to describe something that hasn't failed but rather has been a target of little interest. And it has nothing to do with Linux.

Re: Kenny was a wise man!
 

I'm happy to have provided amusement.

I think it has a lot to do with Linux. I don't think it's accurate to say it has been of little interest. Kindles have text to speech and they are based on Linux, for example.

Re: Kenny was a wise man!
 

It has nothing to do with Linux because Linux is no one thing (at least, not in common parlance.)

Text to speech is different from speech to text (voice recognition.) TTS has been a solved problem for a while, and there are numerous solutions in Linux. Speech to text is much more difficult and requires more specialized knowledge that doesn't have much presence or interest in the various open source communities.

Heck there's a whole article on it at Wikipedia:
http://en.wikipedia.org/wiki/Speech_...ition_in_Linux

Re: Kenny was a wise man!
 

There are actually things happening in the voice recognition area on Maemo right now. Look here: http://talk.maemo.org/showthread.php?t=72565

Re: Kenny was a wise man!
 

Heck, thanks for explaining the difference between text to speech and speech to text. I do own several copies of Dragon NaturallySpeaking, including the very pricey Dragon NaturallySpeaking Professional, and I also own several versions of TextAloud, the best Windows text to speech program, so I do have an idea of the difference. I've been using them for maybe ten years, and I have purchased the best Linux versions of Text to Speech software, which is why I say that they suck. I've also played with Festival and the like. It is always possible that great Linux software that does this stuff has sprung up relatively recently; I hope so, but I doubt it.

It's amazing to me that you pointed to the Wikipedia article on speech recognition in Linux but forgot to mention that it confirms what I said: it sucks in Linux.

And as for text to speech, can anyone point to good voices in Linux? Mostly, the answer I have received when asking year after year is "no".

Re: Kenny was a wise man!
 

Yes, I've seen PocketSphinx mentioned from time to time and will be delighted if it ever really goes anywhere, but when I get decent voice recognition on the Linux systems I run at home I will be more hopeful.