Below are samples for Piper, a fast and local text to speech system. Samples were generated from the first paragraph of the Wikipedia entry for rainbow.


Quality

Voices are trained at one of 4 "quality" levels:

Multi-Speaker

Some voices contain multiple speakers, which captures the style of multiple people within a single model.
Multi-speaker models can quickly switch between different speakers, but the quality of an individual speaker may be less than a single speaker model.