text-to-speech

[tOsYZYny]

I am exploring text to speech and am looking at either espeak or festival. Espeak works out of the box, but it sounds terrible to me (very computer / robotic and the phonemes do not sound smoothly constructed, there is a little bit of static between them). I also looked at festival which does appear to sound better (at least from what I listened to on youtube); however, after installing that (and a language), I am getting "Can't access NAS server".

1. Is it just me, or is there static between phonemes with espeak?
2. WIth Festival, how do I get past the "Can't access NAS server" error? I set the default voice to get past that original error, so there is a voice installed. Is it looking for a server somewhere?

 

[T-Daemon]

2. WIth Festival, how do I get past the "Can't access NAS server" error? I set the default voice to get past that original error, so there is a voice installed. Is it looking for a server somewhere?

From audio/festival manual:

...
If you get the error message

Can't access NAS server

You have selected NAS as the audio output but have no server running on that machine or your DISPLAY or AUDIOSERVER
environment variable is not set properly for your output device. Either set these properly or change the audio output device
in ‘lib/siteinit.scm’ as described above.
...

 

[tOsYZYny]

Thanks.

(Parameter.set 'Audio_Method 'sunaudio)

did the trick

I still am getting a bit of static between phonemes with festival (and espeak). It seems it isn't festival or espeak, but must be my system. Is that normal?