What AI says about eSpeak

eSpeak is a compact open-source text-to-speech synthesizer that supports English and many other languages on Linux and Windows, with ports to Android, macOS, and Solaris. It uses formant synthesis to keep a small footprint (about 2 MB for the program and data) and is available as a command-line program, a shared library, and a Windows SAPI5 component, with WAV output and SSML/HTML support. It converts text to phonemes with pitch and length information, can front-end MBROLA voices, and welcomes native-language data contributions to improve languages.