Speaker identity plays an important role in human communication. In addition to the linguistic content, speech utterances contain acoustic information of the speaker characteristics. This book describes voice conversion, a technique that aims at changing the voice of one speaker (a source speaker) into the voice of another specific speaker (a target speaker) without changing the linguistic information. The relationship between the source and target speaker characteristics is learned from the training data. Voice conversion can be used in various applications and fields: text-to-speech systems, dubbing, speech-to-speech translation, games, voice restoration, voice pathology, etc. The book provides up-to-date information for readers interested in voice conversion. It gives an overview of the field and gives insights for the future in the field.