Text to Speech software

[Ralf Mardorf]

On Thu, 2024-07-04 at 04:00 +0200, Ralf Mardorf wrote:
> On Wed, 2024-07-03 at 23:35 +0100, Grizzlly via ubuntu-users wrote:
> > Hi
> > 
> > Looking for good  "Text to Speech" software, would like something that does not 
> > sound like Stephen Hawkins trying decide on lunch choices but is not too hard 
> > to install and setup, a search around the net found ESpeakm all others I found 
> > seemn to be aimed at software devs to combine in other projects, and need very 
> > high coding levels to use (so really a /w dev)
> > 
> > I don't mind if it's CmdLine or GUI, but it should sound natural(ish) Enflish 
> > is fine so multi-language support is not that important, a few voices would be 
> > nice, but a good male & female will do at a push
> > 
> > thanks
> > 
> 
> Semi-off-topic
> 
> I can hardly watch highly interesting documentaries on German television
> anymore because the "natural" (artificial) speakers always sound like
> they're having a stroke twice per sentence. I can't stand it in the long
> run and have to switch off the documentaries. I suppose I could cope a
> bit longer with the C64 SAM or the slightly better Hawkins robo voices.
> There used to be a few female speakers on the iPad who sounded really
> good as long as they didn't speak slowly. In particular an artificial
> Irish woman, IIRC "Karen". When she spoke slowly, she also sounded like
> she had a stroke or brain surgery. Apple has now replaced the pleasant
> voices that sounded nice when speaking quickly with horrible-sounding
> voices. I can't imagine that there is anything more tolerable under
> FLOSS.

PS:

It's even worse with artificial speech than with artificial lettering in
comics. IMO it doesn't work yet.