Product

About the OpenVoice

OpenVoice is an open-source voice cloning model developed by MyShell, in collaboration with MIT and Tsinghua University. It enables the replication of a speaker's voice using a short audio sample, supporting multiple languages and accents. The model offers granular control over voice styles, including emotion, accent, rhythm, pauses, and intonation. Notably, OpenVoice supports zero-shot cross-lingual voice cloning, allowing the generation of speech in languages not present in the training dataset.