yweweler / single-speaker-tts

This is a single-speaker neural text-to-speech (TTS) system capable of training in a end-to-end fashion. It is inspired by the Tacotron archicture and able to train based on unaligned text-audio pairs.
13Updated 6 years ago

Alternatives and similar repositories for single-speaker-tts:

Users that are interested in single-speaker-tts are comparing it to the libraries listed below