|
Rockbox mail archiveSubject: Re: voice file generation (Re: english.voice using AT&T Natural Voices)Re: voice file generation (Re: english.voice using AT&T Natural Voices)
From: Rocker <rocker_at_shaw.ca>
Date: Fri, 02 Apr 2004 20:33:39 -0700 - Daniel Gudlat said: With talkbox now included, Rockbox kicks some serious ass. Thanks to all the developers and especially Jörg! Yes thanks for the Voice UI Jörg rocker ----- Original Message ----- From: "Daniel Gudlat" <gudlat_at_web.de> To: <rockbox_at_cool.haxx.se> Sent: Friday, April 02, 2004 3:07 AM Subject: Re: voice file generation (Re: english.voice using AT&T Natural Voices) Jörg wrote: > I have made a new program to generate the voice clips, see my tool > collection: > http://joerg.hohensohn.bei.t-online.de/archos/speech/voicefont/authoring_tools/ > The new one is "lang2wav", which generates the whole bunch of speech clips > as .wav without a 3rd party program like TextAloud. Input is the .lang file, > it uses the default voice as configured in the Control Panel. After running > it, you can batch-encode (maybe first batch-trim) the lot and run "voicefont" > to make the final language file. Result should be not larger than 1.5 MB, else > tune the encoder parameters. So the process is pretty simple now, and > lang2wav is way faster than TextAloud. > > We're still waiting for a volunteer to do something similar under Linux with > e.g. the "Festival" TTS program, hint, wink. This could then be part of the > automated build. Mind that I'm not making any promises here, but due to my inability to get the SAPI stuff to work on my Win98SE/98lite installation (the mp3ClipGen.vbs kept on telling me I didn't have SAPI installed, although I had and the speech control panel even let me test some of the L&H voices), I've gotten festival to run on my Gentoo Linux installation instead late yesterday evening. I've also hacked up a shell script to do what mp3ClipGen does. It still has a bug and a few rough edges (e.g. I'd like to be able to select the voice, although I'm sure I'll personally stay with the arctic_slt voice, it's the best festival voice I've found so far; and it relies on the festival server already running on the local server and default port), but will get finished over the weekend, hopefully. If there's any time and energy left after this, I'll give the voicefont generation a try. And in the unlikely event that there's even more time and energy left, I may try producing a german.voice using the adaption of festival to German. If anyone thinks they can do better in the reliability or timeliness departments, don't let this stop you! ;-) PS: With Talkbox now included, Rockbox kicks some serious ass. Thanks to all the developers and especially Jörg! Greetings, -- Daniel Gudlat _______________________________________________ http://cool.haxx.se/mailman/listinfo/rockbox _______________________________________________ http://cool.haxx.se/mailman/listinfo/rockboxReceived on 2004-04-03 Page template was last modified "Tue Sep 7 00:00:02 2021" The Rockbox Crew -- Privacy Policy |