Simple unit-selection speech synthesis for English language is taken apart in this interesting blog post.
https://kastnerkyle.github.io/posts/bad-speech-synthesis-made-simple/
With some caveats, the above blog post represents the algorithm used in tamil-tts project (e.g. ). and demoed at tamilpesu.us/tts_demo
Adding formant synthesis will improve this simple TTS. Are you a ECE/EEE/CS/Mathematics or Engineering undergraduate student interested to improve this code ? Do you want to learn more about filters ? Or, do you have another person in mind ?
Just drop me a line <ezhillang@gmail.com>