Here's what the raw data of the unit selection db file for SpeakEasy sounds like. It gives you a good idea on how unit selection synthesis works.

Quick demo of Black Ice Software's SpeakEasy TTS synthesizer from 1999.

All languages for BeSTspeech have been found (with Arabic not working for some reason). Here's a demo of them in action.

Demo of the 2005 BeSTspeech DLL, known as TTS_ENG.DLL. Taken from the Lingvosoft Talking Dictionary 2006 program. The more I listen to it, this might be the same one that the Franklin LM4000 talking dictionaries used.

All PCM sounds from MacinTalk 3 extracted.

Raw PCM glottal pulse sound extracted for the MacinTalk Bells voice

This was quite amusing. BeSTspeech would work well as a wolf simulator.

ComfyUI AI style edit of an old drawing I did using Kid Pix.

Two AI images from the "flamin' arena" set generated with the qwen image model.

Somewhat failed yet somewhat successful attempt at a ControlNet image generation. Notice how the controlnet drawing shows up as white lines.