Actually I just recently built a Bayonne phrasebook voice library with cepstral voices (voices-proto), so that other TTS generated prompts could be matched up by voice. The only thing you need to do is run audiotool --trim --padding=2 to strip lead and trailing silence, so the prompts merge together well.
If you mean execute cepstral theta from Bayonne2, you can do that either from ttstool or from the "tts" virtual macro from scripting if you configure your virtual for theta. You can then pass arbitrary strings and synth or play prompts. julian howard wrote: >I'd like to use Cepstral tts voices if possible. What >are your thoughts? How would you compare the current >voices to Ceptral's? > > > > >__________________________________ >Yahoo! Mail - PC Magazine Editors' Choice 2005 >http://mail.yahoo.com > > >_______________________________________________ >Bayonne-devel mailing list >[email protected] >http://lists.gnu.org/mailman/listinfo/bayonne-devel > >
begin:vcard fn:David Sugar n:Sugar;David org:GNU Telephony email;internet:[EMAIL PROTECTED] tel;work:+1 201 215 2609 x-mozilla-html:FALSE url:http://www.gnutelephony.org version:2.1 end:vcard
_______________________________________________ Bayonne-devel mailing list [email protected] http://lists.gnu.org/mailman/listinfo/bayonne-devel
