Artificial intelligence-based speaking expression synthesis method and related device

The embodiment of the invention discloses an artificial intelligence-based speaking expression synthesis method and a related device. The method at least relates to various technologies in artificial intelligence, and comprises the following steps: determining a text feature corresponding to the text content and the duration of a pronunciation element identified by the text feature for the text content sent by a terminal, and obtaining the text feature and a target expression feature corresponding to the duration of the identified pronunciation element through an expression model; and returning the target expression feature to the terminal. The expression model can determine different sub-expression characteristics for the same pronunciation element with different durations in the text characteristics. The change pattern of the speaking expression is added. The speaking expression generated according to the target expression characteristics determined by the expression model is matched with the expression of the speaker, and the speaking expression of the same pronunciation element has different change patterns, so that the condition that the change of the speaking expression is excessively unnatural is improved, and the immersion feeling of a user is improved.