What AI software do people use to make those sound effect voices (like making Minecraft villagers speak, or making celebrities sing songs)?

I'm trying to make a voice for a robot, and I want the voice to be created using the robot's sound effects. I was thinking there was some program to input audio files and then use text to speech or a speech sample to make the sound effects "speak English" like those Minecraft villager talking videos made with the villager's sound effects.