[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Emacspeak and Cepstral TTS

Hi All,

I just wanted to ask if anyone out there in the emacspeak community
has been experimenting with Cepstral's TTS (theta)?

The reason I'm asking is that over the last two days, I have hacked
together a TCL shared library and basic TCL interface for emacspeak
using Cepstral's theta TTS engine and thought it was worth checking to
see if anyone else has been working on anything similar as it might be
worth coordinating efforts. 

For those who are not aware of Cepstral (http://www.cepstral.com),
they have produced a number of very high quality voices and a basic
TTS engine. The system is mostly compatible with festival, but they
have created a higher level TTS called theta. The Cepstral voices are
very resonably priced - about $40 per voice (you can make do with just
one voice) or about $250 for their SDK. I only purchased a single
voice. With the voice, you get their theta shared libraries and header
files together with some basic documentation. I'm not exactly sure
what you get with the SDK. 

With the single voice I purchased and the libraries/headers, I've
managed to put together a very basic emacspeak server. It does not
support many emacspeak features at this stage (no voice locking,
tones, etc), but it does look promising. I plan to release the code
once I've got it to a stable point. Cepstral themselves have been very
supportive and have no problems with me releasing my code as open
source and have offered technical support to help in the development. 

So, if anyone else has purchased one of the Cepstral voices, I'd be
interested in hearing from you. Maybe we can work together or you can
help me test the server and chase down bugs (or just report them!). 


To unsubscribe from the emacspeak list or change your address on the
emacspeak list send mail to "emacspeak-request@cs.vassar.edu" with a
subject of "unsubscribe" or "help"

Emacspeak Files | Subscribe | Unsubscribe | Search