Apropos of my last post, here’s an sample of the same paragraph, part of an earlier post here, rendered in various text-to-speech systems. All samples have been converted to MP3 files (using iTunes) for ease of comparison:
- IBM Text-to-Speech: Unconstrained U.S. English Text Demo
- AT&T Natural Voices Demo
- Festival Voice Demo
- Winbond USA TTS Demo
- Testen Sie die ATIP Sprachsynthese interaktiv
- Mac OS X Built-in Speech
To my ears, the IBM female voice is the best sounds — it has a certain melodic quality that’s quite pleasant. The AT&T speakers are very good too, if a little over-zealous. Winbond can’t really be faulted for its poor quality — it’s a “TTS on a chip” system, not a general purpose software system.
About This Blog
I am Peter Rukavina and this is my blog. I am a writer, letterpress printer, and a curious person.
To learn more about me, read my /now, look at my bio, listen to audio I’ve posted, read presentations and speeches I’ve written, or get in touch (peter@rukavina.net is the quickest way).
You can subscribe to an RSS feed of posts, an RSS feed of comments, or a podcast RSS feed that just contains audio posts. You can also receive a daily digests of posts by email.
Comments
The “Festival Demo” voice is
The “Festival Demo” voice is the one which sounds the most like what I imagined a computerized voice would sound like — like Stephen Hawkin’s.
It also reminds me so much of the “Fitter Happier” track from Radiohead’s OK Computer record — eerie, actually. Most of the other samples sound quite natural, all considering.
Add new comment