WarpMyMind

Hi -

I want looking for software to convert a text file into a voice. The best I found, which was not good, was an IBM Watson application that produced so-so files.

What TTS software do wwm people use? Where do you all get the voices (I like sexy UK girl voices myself? Does your software allow you to adjust pronunciation of tricky phrases?

I'd like to write some of my own stuff, but I need some decent TTS voices and sound edition software to get started, so any help is appreciated.

Thanks,

jan

I reposted this in the File Making and Hypnosis Techniques forum, where it is more appropriate, I think.

Thanks,

jan

jan wrote
Hi -

I want looking for software to convert a text file into a voice. The best I found, which was not good, was an IBM Watson application that produced so-so files.

What TTS software do wwm people use? Where do you all get the voices (I like sexy UK girl voices myself? Does your software allow you to adjust pronunciation of tricky phrases?

I tried a few websites on Google's first few pages of response to my results for "test to speech software free". In my limited opinion, the best free TTS I found was found at http://www.fromtexttospeech.com/ ... and the best voice there was Emma [British English]. The Slow setting works best for hypnosis files. The technical specification of this voice is [Contributing Artists: TextAloud: IVONA Amy22 (UK English)]. All the voices on this site seem to be labeled Name22. The US voices mispronounced "base" (as in "baseball") as "bass" (as in the large-mouthed or small-mouthed fish). I'd love to find a good US Voice with either a Southern drawl or a Boston Irish accent.

Audacity is free -- I love free -- so I have downloaded the software, but have not thought about cracking the Owner's Manual yet.

I also will be watching the replies for tips.

I'm kind of interested in knowing what's good these days, since my knowledge of TTS software is a few years out of date. In 2011-2012 or so, the best deal I could find on it was Cepstral's software, but I get the feeling I didn't do enough research back then. I especially want to know if software these days handles rhythm and speech prosody better, since that's always been kind of a problem even if you go to the trouble of sculpting every syllable.