I tried to find an easy and simple text to speech program. Wrong! gotta remove the word easy. There is nothing easy about text to speech, even just finding a good working one. ttsreader.com just wants you to come to their site every time you need something converted, although they are not bad. As a developer I’m looking for something different.
I didn’t see where to easily download the audio file I would have created. So I kept it moving. Moving on to do some more research, where I then came across googles Tacotron which is quite impressive. Since I want the information to remain proprietary, I kept looking. It’s been at least five years since I delve into the inner workings of text to speech. I came across a quora article that made me realize that may tts isn’t the right term anymore it might be Speech synthesis. Before long I was looking at Amazon’s Polly. It’s a service I’m looking for software that I can incorporate into may applications. I think I just prefer the opensource community but I’ll definitely go for a some kind of closed source or package or service. I realize that this segment of the computer industry text to speech had to have advanced a lot with the advent of a applications like Siri and Alexa. Having started to get into the more complicated side of things I realized that simple text to speech and speech to text had to have had AI incorporated into it in order for it to work. The way a person pronounces a word or emphasizes parts of a sentence have a lot of nuances. It may be something too big for me to take on by myself. Maybe I just need to use someones service. Speech Synthesis Markup Language (SSML) scared me. I don’t need another mark up language.
When I last investigated this field it was more an opensource initiative, continuing to dig around in Quora…
————— https://www.quora.com/What-is-the-best-text-to-speech-software ————-
There has been a tremendous amount of discussion on Quora about this already. Note, that Wikipedia has defaulted to the terminology of, instead of TTS. For that matter, Wikipedia contains a . BTW, is a good person to follow on Quora for speech technology answers.
above is a quote from some person who no longer contributes to Quora it was useful. Nickolay Shmyrev is really knowledgeable on the topic as suggested. I almost want to go through and read all the questions he answered.
The Quora article led me to Wikipedia which had the comprehensive source of course on speech synthesizers. At this point I’m going to dig into ESpeak and see what it can do. Review. youtube.com/watch?v=WuuQzmh03vI and youtube.com/watch?v=-iQllxgtkzE. Amazon has a whole developer guide for Polly . IT looks like Polly was Ivona.