Is it possible these days to, say, record yourself pronouncing every consonant and vowel in your target language, and then using those sound snippets to dynamically generate the pronunciation of words and such? I am looking to produce 22 consonants with 5 vowels, so 110 combinations/pairs, at each of 12 notes, so over 1000 sound snippets, which is like an hour of pure recording.
Is there some way somehow to use some tool to turn these primitive sound snippets into full on words / text-to-speech? Or is there a big gap between having these sounds and making them work in an existing open source library? If it's not possible to use a simple library and plugin your own voice, what are the high-level steps you would take to make it possible by hand or writing some custom software?
Sort of like this:
Emvoice takes a different approach. We've broken record vocals down to the granular level, recording the elements that make up individual phonemes at multiple pitches. Thousands of samples are reconstructed by a sophisticated cloud-based engine that returns the complete vocal to your system over the internet. What you're hearing when you listen to Emvoice One isn't artificial - it's a real singer's voice interpreting your own words.
But plugging in your own voice.
