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, and the method comprises the steps: carrying out the content extraction of a to-be-converted voice, and obtaining a target feature; encoding the target feature to convert the target feature into a target vector; target rhythm parameters corresponding to the to-be-converted voice are obtained, the target vector is decoded on a target tone according to the target rhythm parameters, the Mel-Per features of the target tone are obtained, and the target rhythm parameters do not contain the tone of the to-be-converted voice; by removing the timbre of the to-be-converted voice contained in the target rhythm parameter, the problem that the timbre of the original speaker is leaked into the converted voice due to the fact that the feature of the to-be-converted voice is directly used for generating the Mel-Per feature, and thus the effect timbre after voice conversion is different from the timbre of the target speak