A method for real-time lip synchronization is provided. The method transmits, by one or more processing devices, a requested document comprising embedded instructions to a client device. The one or more processing devices generate a plurality of phonemes responsive to an additional request from the client device. The one or more processing devices transmit the plurality of phonemes to the client device responsive to the additional request. The embedded instructions direct the client device to generate animation models and transition models based on the plurality of phonemes.
展开▼