audio-video dialog

January 20 news, Beijing Shangtang Technology Development Co., Ltd. today announced that its "Rizhixin fusion big model interactive version" (SenseNova-5o) officially provide real-time audio and video dialogue services to the outside world, free of charge for a limited period of time. According to the introduction, this model is the interactive version of SenseNova's "Day by Day" fusion model, which supports real-time interaction, visual recognition, memory thinking, continuous dialog and complex reasoning, and can help AI communicate with humans in a more natural and fluent way. We also provide the supporting Realtime API for "SenseNova-5o"...