On August 9th, ByteDance's cloud computing service platform, Volcano Engine, announced that Douyin's large-scale model supports real-time voice calls. According to reports, Volcano Engine launched a dialogue-based AI real-time interaction solution, which is equipped with the Volcano Ark large model service platform. It uses Volcano Engine RTC to collect, process, and transmit voice data, and deeply integrates Douyin's speech recognition and speech synthesis models. The process of converting speech to text and text to speech is simplified, providing intelligent dialogue and natural language processing capabilities to help applications quickly realize real-time voice calls between users and cloud-based large models.