Piper Voice Samples

DRANK

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.QualityVoices are trained at one of 4 "quality" levels:x_low - 16Khz audio, 5-7M paramslow - 16Khz audio, 15-20M paramsmedium - 22.05Khz audio, 15-20M paramshigh - 22.05Khz audio, 28-32M paramsMulti-SpeakerSome 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.