[Asterisk-Users] Speech recognition or TTS with Asterisk?

[Paul]

trixter aka Bret McDanel wrote:

>On Thu, 2005-11-17 at 14:56 -0500, Paul wrote:
>  
>
>>I provided the link for phpagi. Install it and install festival. Set up
>>an extension going to the weather.php demo.
>>    
>>
>
>  
>
>>If you want this running real soon contact me offlist about paid
>>services. Otherwise you will be reading and learning. Free help via the
>>list happens while I am taking coffee/donut breaks so patience is a
>>needed virtue.
>>
>>    
>>
>
>Sadly I found festival easy to set up but really hard to understand what
>its saying.  Unless you are super dedicated to tweaking festival to
>sound better than speak and spell I would suggest using any number of
>the paid services.  
>
>On my webpage I wrote an article talking about how to integrate IBMs TTS
>engine into asterisk.  Its a shell script and a simple macro to call it.
>Really trivial, but it sounds WAY better.
>
>I would also like to add that it appears IBM moved their system, I will
>see if I can hunt down the new site for their TTS demo ...  Their new
>demo has more voices so that would be a good thing.  
>
>IBM doesnt sound the best but it is better than festival, and due to the
>old license anyway, the same cost :)
>  
>
I use the british male speaker voice. It sounds only slightly better.

Nobody listening to my demo has ever accused me of using recorded human
speech. They definitely believe it is synthesized. If you follow the
links from the festival home page(somewhere at cmu.edu), there are some
demos of much better voicing.

If you just want a "functioning placeholder" for whatever you are trying
to prototype/develop, festival is a good start. Get some interactive
extensions working and look for alternatives when you have time(or money
to delegate the task).