Voice conversion method and device, electronic equipment and storage medium

The invention relates to a voice conversion method and device, electronic equipment and a storage medium. The method, which is used for converting the voice of a source speaker into the voice of a target speaker, comprises the steps of: obtaining the voice of a source speaker, and determining the text of the source speaker according to the voice of the source speaker; and inputting the text of the source speaker into a voice synthesis model and a duration forced alignment model of a target speaker to synthesize the voice of the target speaker. A spectrum feature prediction module comprises a duration model and an acoustic feature module. The voice of the source speaker is subjected to forced alignment through the duration forced alignment model to obtain the forced alignment duration information of the source speaker, the duration predicted by the duration model is adjusted by using the forced alignment duration information to obtain adjusted duration information, and the voice of the target speaker is synthe