Panther and Vicki

Posted:
in macOS edited January 2014
Reading this forum and various other forums, I see that there will be a new high quality voice added to Panther called Vicki. I am unable to speak due to a stroke at the age of 13 and I use Apple's text to speech to speak with friends over the phone using the Fred voice (and now that I own an iSight, as of last week, it would be nice to use text to speech to communicate with people I video chat with). Needless to say that I am very much interested in Apple's text to speech abilities. I saw that someone wrote that not even Vicki compared to voices that AT&T uses. The person left the URL of the demo to hear the AT&T voices. Another person had a link to a demo of Vicki. They are right, AT&T's voices sound better than Vicki or any of the other text to speech voices that Apple uses. Some were speculating that Vicki's huge file size means that some time down the line that Apple will be upgrading their text to speech abilities either in one of the incremental upgrades of Panther, or maybe it will mean a new iApp.



I would like to hear other people's opinions on where Apple's text to speech abilities, or rather, technology is going.
«1

Comments

  • Reply 1 of 23
    stoostoo Posts: 1,490member
    There was an article in MacFormat (UK Mac mag) about a patent Apple filed recently for adding characterisation to voice synthesis, to make it more personalised. I'll have a look for it.
  • Reply 2 of 23
    jwilljwill Posts: 209member
    I'm willing to hear the new voice. Come forth, Panther!



  • Reply 3 of 23
    murkmurk Posts: 935member
    I keep bringing this up, if only for the reason that Steve Jobs said that Apple was in the market for an improved text-to-speech engine. That statement was made over a year ago. Could it be that ATT's voices are too expensive for Apple? Rhetorical TTS is another possible choice. Mac Slash mentioned that Apple was hiring for a Screen Reader app for the blind. Hopefully this and the patent mentioned above mean the improvements will come eventually. Mac Slash



    http://www.rhetoricalsystems.com/
  • Reply 4 of 23
    I wouldn't mind hearing a new Dalek voice! m.
  • Reply 5 of 23
    I would hope that any Apple research in this area would build upon open-source efforts such as:



    http://festvox.org/

    http://www.cstr.ed.ac.uk/projects/festival/
  • Reply 6 of 23
    mlnjrmlnjr Posts: 230member
    I've heard the AT&T voice demos, but where's a link to a demo of the new Apple voice?
  • Reply 7 of 23
    placeboplacebo Posts: 5,767member
    To tell the truth, I listened to a smple of Vicki and I was pretty impressed. It's still very "cyborg", but it's almost to the AT&T level.
  • Reply 8 of 23
    Here is the link to the Vicki voice:



    http://verdens.navle.no/musikk/fitter.vicki.aiff
  • Reply 9 of 23
    mlnjrmlnjr Posts: 230member
    Thanks, ginopiazza49.



    Vicki sounds like a slower, slightly smoother version of Victoria, and neither of those sound as lifelike as the AT&T voices to me.
  • Reply 10 of 23
    lucaluca Posts: 3,833member
    Vicki sample.



    Hope this helps. It's not really that great, it just seems to reduce the occurrance of some of the strange noises you hear when the computer is talking.



    EDIT: Beat me to it!
  • Reply 11 of 23
    Quote:

    Originally posted by Placebo

    but it's almost to the AT&T level.



    Hardly. I've heard other voice-synthesizing software that sounds FAR better than this. Apple has made just marginal improvements to the voice system. Most of the same old problems in Macintalk are still present. It just sounds like Apple's using a higher sample rate or something of the like. Bleh.
  • Reply 12 of 23
    cakecake Posts: 1,010member
    Heh.

    Vicki likes Radiohead.
  • Reply 13 of 23
    aquaticaquatic Posts: 5,602member
    It sounds more lifelike but there are still blips in it. Why does it have to make all those intermittent blips, I thought that used to be because it required a lot of computer power (back in 68k days.) The voice itself is hot, but the blips suck and it still sounds a little whiny in parts. Yeah it's like Victoria 2.0.



    Quote:

    FestVox version 2.0: Jan 2003: new in this release



    Better clunits general voice support





    Support for CMU Sphinx and SphinxTrain to build acoustic models for labeling





    DOCBOOK version of the documentation, with more general backgfround documentation





    Initial support for Mac OS X





    configure support to match Edinburgh Speech Tools



    Interesting, I wonder if there work will be better then Vicki, or is Apple using this open source? I hope they start using more and more open source to save money and build up a good rep.



    Anyone have any samples of other, better, solutions?
  • Reply 14 of 23
    david rdavid r Posts: 135member
    AT&T voice demos. Have fun.



    http://www.naturalvoices.att.com/demos/
  • Reply 15 of 23
    cakecake Posts: 1,010member
    That is hilarious.



    Try making that white voice sound street.

    Much fun.
  • Reply 16 of 23
    jwilljwill Posts: 209member
    The voice is pretty clean and understandable in my opinion.



    If I remember (lol), I'll probably set that to default when Panther comes (even though i don't use Speech a lot anyway...)
  • Reply 17 of 23
    lucaluca Posts: 3,833member
    Actually, Vicki is already set as the default voice in Panther, it being the newest, best sounding one. Victoria used to be the default voice although I always thought Bruce sounded more realistic. None of Apple's voices can hold a candle to those AT&T ones though. Those are amazing. They really only trip up on very long words.
  • Reply 18 of 23
    Wow those AT&T voices are really good. They seem to do german much better than english though..
  • Reply 19 of 23
    aquaticaquatic Posts: 5,602member
    Those AT&T are better but Vicki comes close.
  • Reply 20 of 23
    amorphamorph Posts: 7,112member
    Vicki does a better job of following the arc of a sentence than the old voices do.



    If they could just get rid of those weird "pops" in the voice, it would sound truly impressive - especially for purely synthesized speech, which the AT&T technology is not.
Sign In or Register to comment.