Hi.
May be the following addon and synthesis help you.

Dual Voice for NVDA, is an open source speech driver for NVDA screen
reader. This let use two separate voices for reading non-Latin and
Latin languages. This add-on is compatible with SAPI5 (Speech API
version 5) and MSSP (Speech Platform). This NVDA add-on need one
non-Latin and one Latin voices with common interface. Both non-Latin
and Latin voices must have Speech API...

eSpeak: speech synthesis
Text to Speech engine for English and many other languages. Compact
size with clear but artificial pronunciation. Available as a
command-line program with many options, a shared library for Linux,
and a Windows SAPI5 version.
You get them from:https://sourceforge.net/projects/espeak/and
use eloquence sapi5 for English.