Any links?
Text to speech programs (TTS)
56 Replies, 13553 Views|
Ah, found it:
http://www.cstr.ed.ac.uk/projects/festival/ https://en.wikipedia.org/wiki/Festival_S...sis_System Looks interesting indeed! Thanks!
lots of voices , search festivox as well
New AI powered TTS by Google (Tacotron 2) sounds fantastic!
https://google.github.io/tacotron/public...index.html https://research.googleblog.com/2017/12/...peech.html
I made some progress with TTS programs. It is fun, but the pronunciation and intonation can be way off... Anyway, for those who want to experiment.
(This post was last modified: 05 Apr 2019, 22:34 by Like Ra.)
Get the SAPI5 voices from this magnet link: magnet:?xt=urn:btih:31f696721cdec7975707dfea6f52806dc14fb91d&dn=IVONA+Text+to+Speech+with+crack+%28All+voices%29&tr=udp%3A%2F%2Ftracker.leechers-paradise.org%3A6969&tr=udp%3A%2F%2Fzer0day.ch%3A1337&tr=udp%3A%2F%2Fopen.demonii.com%3A1337&tr=udp%3A%2F%2Ftracker.coppersurfer.tk%3A6969&tr=udp%3A%2F%2Fexodus.desync.com%3A6969 The explanations how to make it work and replace the DLL:
How to get Ivona Text To Speech For Free Forever 2017-2018-8R3G7KsBt_M.mp4 (Size: 9.48 MB / Downloads: 318)
For Microsoft Speech Platform voices install: Microsoft Speech Platform https://www.microsoft.com/en-us/download...x?id=27225 Voices https://www.microsoft.com/en-us/download...x?id=27224 Install Balabolka TTS program: http://balabolka.site If you are on Linux, the procedure is a bit longer. You need 32-bit version of wine prefix. sudo dpkg --add-architecture i386 export WINEARCH=win32 export WINEPREFIX=~/.wine32 sudo apt-get install winetricks Install XML fix: winetricks msxml3 Install SAPI5 support: winetricks speechsdk At least it worked for me 😉
More TTS voices here: https://nvda.ru/sintezatory-sapi5
I use Natural Reader on windows. I'm working on a "Self bondage directed by computer generated directions", it's a lot of fun.
DBF
I know its not quite the same as the original question... but I started playing with TTS for IOS yesterday.
ended up going with the Pro version of Natural Reader... It can read from Websites etc and I had it read me about a 5hrs story from Gagged Utopia today while on a very Driving intensive day.. When It first started reading the story I thought i would not be able to tolerate it for very long, but eventually tuned in to it just fine. It was a story I had started reading but it was very long and never got around to finishing it... having it read to me was much easier.
Free Open TTS RHVoice
(This post was last modified: 10 Jun 2019, 00:12 by Like Ra.)
https://github.com/Olga-Yakovleva/RHVoice For Windows users: https://github.com/Olga-Yakovleva/RHVoic...st-version Quick tutorial for Linux users. Just compiled it on Linux - works perfectly! https://github.com/Olga-Yakovleva/RHVoic...g-on-Linux Install prerequisites: sudo apt-get install scons gcc git flite flite1-dev expat libunistring-dev libsox-dev libpulse-dev libao-dev build-essential libc6-dev g++-multilib -y Clone: git clone https://github.com/Olga-Yakovleva/RHVoice /var/tmp/rhvoice Compile and install: cd /var/tmp/rhvoice scons sudo scons install sudo ldconfig Test in English: echo "Put on shiny latex pantyhose, tight latex leotard, high heels and dance around." | RHVoice-test -p SLT Test in Russian: echo "Алиса, включи освещение в доме и надень колготки." | RHVoice-test -p Anna To save in a file: echo "Put on shiny latex pantyhose, tight latex leotard, high heels and dance around." | RHVoice-test -p SLT -o 1.mp3 To tweak: (Increase both pitch and tempo to 120%): echo "Put on shiny latex pantyhose, tight latex leotard, high heels and dance around." | RHVoice-test -t 120 -r 120 -p SLT Voices: https://bintray.com/olga-yakovleva/RHVoice Global configuration file: /usr/local/etc/RHVoice/RHVoice.conf
A good summary on Russian TTS in English 😁 : https://forum.duolingo.com/comment/14224...h-software
(This post was last modified: 14 Jun 2019, 22:55 by Like Ra.)
And another one: https://4pda.ru/forum/index.php?showtopi...28&st=1800 |
| Possibly Related Threads… | |||||
| Thread | Author | Replies | Views | Last Post | |
| Speech-to-text/speech recognition programs (STT) | Like Ra | 19 | 4,426 |
08 Sep 2025, 18:35 Last Post: Like Ra |
|
| Elevenlabs now lets you create A.I. voices from text prompts | AI_addict_hypnofan | 0 | 182 |
26 Jun 2025, 10:47 Last Post: AI_addict_hypnofan |
|
| AllTalk TTS | Like Ra | 31 | 2,138 |
29 Apr 2025, 13:37 Last Post: brandynette |
|
