We stand with Ukraine to help keep people safe. Join us
Cepstral Voices
Cepstral Voices
2.7
0.0
HomeMusic & AudioCepstral Voices
Cepstral Voices free download for Mac

Cepstral Voices

Version 6.2.3

Voices for handheld, desktop, and server applications.

2.7
Based on 5 user ratesRead reviews & comments

Cepstral Voices overview

Cepstral Voices provides voices for applications. Cepstral is a speech technology company based in Pittsburgh, PA, USA which provides speech technologies and services for the spoken delivery of information. We build high quality, natural sounding voices (which integrate directly with the Apple Speech Manager) for hand-held, desktop, and server applications. Cepstral: We Build Voices.

What’s new in version 6.2.3

Updated on Aug 29 2013

Version 6.2.3.:
  • Natural prosody and smart pronunciation
  • Enhanced audio
  • New voices:
    • Allison now has 20% more source material, making this favorite even better!
    • Alejandra is a new high quality Americas Spanish voice.
    • Charlie is a youthful US English male voice with personality
    • The character voices Dallas and Belle are now available for Windows.
  • Superb OS integration

Information

License

Demo

Size

191 MB

Developer’s website

http://www.cepstral.com

Downloads

27965

App requirements

  • Intel 64
  • Intel 32
  • Mac OS X 10.6 or later
Try our new feature and write a detailed review about Cepstral Voices. All reviews will be posted soon.

Write your thoughts in our old-fashioned comment

MacUpdate Comment Policy. We strongly recommend leaving comments, however comments with abusive words, bullying, personal attacks of any type will be moderated.
0.0

(0 Reviews of )

There are no reviews yet
  • Comments

  • User Ratings

Lesoth0
Lesoth0
Dec 3 2014
6.2
0.0
Dec 3 2014
0.0
Version: 6.2
Have always really liked the CEPSTRAL DIANE voice as it sounds like the actress from Desperate Housewives and Dallas.
kosovarnye@yahoo-com
kosovarnye@yahoo-com
Aug 30 2013
6.2
0.5
Aug 30 2013
0.5
Version: 6.2
I purchased the "Laurence package," version 4, which gives a reasonable facsimile of british english, but that's where my praise ends! I deleted it because Apple's "Alex" sounds more human. I could see no improvements when I tried version 6. It was annoying to be reminded every 20 seconds right from the start that I had not upgraded. Cheapskates! Why upgrade? It is no better. Then, after I uninstalled it using the command in the preference pane and switched back to Alex. It continued to speak only the Laurence voice. It's not enough to be mediocre and expensive software, but once you install it, you can't easily get rid of it. Beware!
Sean-Smith
Sean-Smith
Aug 28 2013
5.2
4.0
Aug 28 2013
4.0
Version: 5.2
Cepstral Voices 6 has been out for a couple of months now. The current version is 6.2.3.685.
Aikousha
Aikousha
Mar 1 2011
5.2
0.5
Mar 1 2011
0.5
Version: 5.2
Downloaded DAMIEN as the first test, and never got past that one. It was easy to install, and easy to operate, for a character voice it was interesting but very difficult to understand many of the words it was given... but that's not even going to be part of the rating. After quickly tiring of the voice, I attempted to get my regular Apple voices back... but they were totally frakked up, all sounding like someone had bashed a person over the head with a crowbar, and then had their head held under water... for 2 seconds.. and then silence. It did this to ALL the voices, so it obviously screwed up either the engine or the prefpane. So I attempted to try the "super easy to do" complete uninstall. Even though it asked if I was sure, and even though it prompted me for my Admin password (which I gave it), it did absolutely nothing to remove any part of itself from either the prefpanes, the prefs folder, Application support, and wherever else it might have stuck things. It did not remove the prefpane, and the voices were still screwed up. I used FileBuddy to track down 3 parts of it, but could not find the PrefPane for it, and attempting to manually delete it from the System Prefs, just had it telling me that it had to abort removing "%@" because an error occurred. Yes, that's PERCENT-AT ^_^ Searched for that even, but it couldn't find it. It's still there, and I still have frakked voices. The features might be nice, but if it completely screws your system AND won't allow itself to be uninstalled, it's not worth even getting paid to use it. On top of that, the price is extraordinarily high for a voice file anyway. One that intones everything properly, doesn't mispronounce anything, and doesn't get boring, might be worth the price asked, but this didn't do any of that. I'm more satisfied with the Victoria voice that came with OSX (unless the character voice is deliberately of less quality than the other voices.) I'm now going to boot up my emergency partition so I can remove everything from the System disc, that wasn't there Friday, and pray that fixes this. If it corrupted a system file, that'll take about 12 hours for a complete restore. I still really would like a Japanese voice or two that would work with Kanji, but haven't found one, yet. Not that I'd trust this company for one.
kosovarnye@yahoo-com
kosovarnye@yahoo-com
Oct 9 2008
4.2.1
0.5
Oct 9 2008
0.5
Version: 4.2.1
THIS IS OUTRAGEOUS. THERE IS A NEW VERSION OF Cepstral Voices WITH AN UPGRADE FEE. HOWEVER, THERE ARE PAGES AND PAGES OF ISSUES ON THE CEPSTRAL WEBSITE THAT SHOW THAT THIS VERSION 5 DOESN'T WORK and can crash your system. THE VERSION I PAID FOR STOPPED WORKING AND THE NEW VERSION BARELY, BARELY WORKS. WHO WANTS THAT??? THIS SHOWS ALL THE WAYS THAT THE NEW VERSION STILL DOESN'T WORK. IF CEPSTRAL CAN'T SPEND THE TIME AND MONEY TO MAKE THEIR PRODUCT WORK WITH THE NEWEST MACOS, THEY SHOULD ABANDON IT AND STOP RIPPING PEOPLE OFF WHO DON';T KNOW WHAT THEY'RE PAYING FOR!!! HERE IS AN ABBREVIATED LIST OF DEFICIENCIES IN THIS SOFTWARE THAT IS POATED ON THE COMPANY'S OWN WEBSITE. AT LEAST THE COMPANY IS BEING UPFRONT BUT THEY STILL WANT TO TAKE YOUR MONEY AND GIVE YOU JUNK IN RETURN. 1. The voices may go silent due to the system's audio properties having been adjusted to incompatible settings. 2. Cepstral voices stop speaking sometimes when used in VoiceOver. They will not speak again through VoiceOver until you log out and log back in. This problem occurs mostly if you use Command+Tab to switch between tasks or if you use Ctrl+Option+D to move the cursor to the dock and cycle through dock items. 3. When reading text copied from Safari, line breaks may occasionally be pronounced as question marks. 4. Word highlighting text positions are wrong when the volume is not set to 1.0. 5. Text position information passed to user callbacks is incorrect with certain settings, causing word highlighting to break. 6. Apple's pronunciation dictionaries are not supported. You can still use cross-platform Cepstral user lexicons, however. 7. Synthesis to phonemes -- the TextToPhonemes() API call -- is not supported. Error and synchronization callbacks are not supported. 8. When stopping speech, the synthesizer will always halt immediately, instead of waiting until the next word or sentence when requested. 9. Tuned phonetic input -- the [[inpt tune]] embedded command -- is ignored. In phonemes mode, all prodosic control symbols, with the exception of primary syllable stress, are ignored. 10. Some linebreaks are pronounced as "dot question mark." 11. If you use the Migration Assisant to transfer data and programs from one Mac to another, including Cepstral voices, your Cepstral voices may not function properly on the new computer. 12. If you enable "Announce the Time" under Date & Time preferences and set it to use a Cepstral voice, you cannot change the voice afterwards, even to a different Cepstral voice. Even if you set it to "Use System Voice," it continues to use your selection. Logging out and/or restarting do not solve the problem. 13. "interpret-as" attributes of "" elements are not properly handled. If the input text contains back-to-back SSML elements, swift only handles the 14. last one in the list. For instance, the following only pauses for three seconds instead of five: 15. RIFF audio files with a sampling rate that differs from the native sampling rate of the voice are not correcly resampled when specified using the SSML element. 16. Applications using Swift TTS exit silently when a sentence that begins with an SSML or tag is fed to a non-US English voice for synthesis. 17. Swift does not currently support the xml:lang attribute of SSML tags that make use of it, such as , , etc. 18. Swift does not reject bad SSML markup. It will complain about blatant syntactic errors, such as missing close tags, but not about semantic errors, such as invalid tags and attributes. 19. The SSML and tags may not have the proper effect. This is supposed to be read as two sentences, but we read it as one: 20. Swift does not currently support the SSML tag for adding additional lexicons. 21. The SSML tag:attribute pair should select a neuter-gendered voice, but it currently does nothing. 22. The "age" attribute to the SSML tag is looking for an exact match, when it probably ought to be looking for the closest match. For instance, will only select a ten-year-old voice, or fall back to the default voice if one is not found. 23. Cannot provide multiple voice selections in the SSML tag. The tag should request David, and use William as a fallback. Instead, Swift interprets as a request for a voice named "David William." 24. The default SSML voice may not be the default voice for that gender. To illustrate, Swift may switch voices while executing the following SSML code, when it should not. 25. Changing voice in SSML resets prosody and pitch. 26. The duration attribute of the SSML tag is not supported. 27. Prosody as specified in the SSML prosody element is not applied to output generated using the SSML phoneme element. 28. Pitch contours passed in via the SSML tag with values not falling between 0% and 100% are supposed to be ignored. Swift attempts to synthesize with these bogus values. 29. SAMPA stress markers in SSML tag not supported. 30. The SSML tag causes a crash in Canadian French, Americas Spanish, and Italian voices. 40. Text position synthesis event information is incorrect when the SSML element is encountered.
papericons
papericons
Mar 18 2007
4.2
5.0
Mar 18 2007
5.0
Version: 4.2
I have been using the Cepstral Diane voice for about a year. Works great and the voice is much better than any of the canned Apple voices. Just a bit more tweaking is all that's needed as there are a few pronunciation errors and a slight wavering can sometimes be heard. All-in-all the application is A #1.
Bubumac
Bubumac
Mar 18 2007
4.2
0.0
Mar 18 2007
0.0
Version: 4.2
For me, the best text-to-speech software is infovox ivox : http://www.assistiveware.com/voicedownload.php?lang=english
Zookeeper
Zookeeper
Jul 28 2006
4.1.2
0.0
Jul 28 2006
0.0
Version: 4.1.2
Compare TTS voices at http://www.tmaa.com/tts/Samples_intro_USEng.htm and you will likely find that Loquendo voices are the best-of-breed.
Abspjl
Abspjl
Jul 8 2006
4.1
0.0
Jul 8 2006
0.0
Version: 4.1
These really are MUCH better than the Mac OS voices. If you use spoken text and spoken alerts much, you will find these natural voices well worth paying for. And they can be tried for free!
Billklee
Billklee
Mar 14 2006
4.0.3.1
0.0
Mar 14 2006
0.0
Version: 4.0.3.1
The demos on their demo page do nothing, and make no sound whatsoever. I'm unimpressed.
Guest
Guest
Sep 24 2005
3.4.2
3.5
Sep 24 2005
3.5
Version: 3.4.2
What are the limitations of the demo voices? It's a big download just to check it out...
Guest
Guest
Apr 11 2005
3.2.1
3.5
Apr 11 2005
3.5
Version: 3.2.1
These voices really are a lot better than the bundled voices from Apple, which haven't changed in years; syllables are clearer, and more natural sounding, and there are non-American accents, which are a welcome option, for some. These voices could make text-to-iTunes/iPod for RSS feeds, reading eBooks etc. truly feasible. (no, nothing to do with the company!)
kosovarnye@yahoo-com
kosovarnye@yahoo-com
Aug 30 2013
0.5
Aug 30 2013
0.5
Version: null
Sean-Smith
Sean-Smith
Aug 28 2013
4.0
Aug 28 2013
4.0
Version: null
Aikousha
Aikousha
Mar 1 2011
0.5
Mar 1 2011
0.5
Version: null
papericons
papericons
Mar 18 2007
5.0
Mar 18 2007
5.0
Version: null
Guest
Guest
Apr 11 2005
3.5
Apr 11 2005
3.5
Version: null