Recently, at the Global Developers Conference (GDC), Mobvoi officially launched its latest product—the Xiaowen Mobile Digital Human. This product attracted the attention of many attendees with its flexible and mobile body, high IQ question-and-answer capabilities, and smooth interactive experience, making it a highlight of the conference.
According to reports, the Xiaowen Mobile Digital Human is an embodied intelligence product carefully crafted by Mobvoi based on DeepSeek, its self-developed large model "Sequence Monkey," and the Qualcomm QCS8550 chip. It not only has a flexible moving "body," but is also equipped with a high IQ "brain," an attractive appearance, natural and realistic voice, and agile, smooth interaction capabilities. These features enable the Xiaowen Mobile Digital Human to gather information, quickly answer questions, and excel in obstacle avoidance and facial recognition.
In terms of application scenarios, the Xiaowen Mobile Digital Human demonstrates broad applicability. It can serve as an AI guide, providing commentary and tour services in exhibition halls, museums, and other venues; it can also function as an AI receptionist, offering convenient consulting services and daily reception guidance for enterprises, governments, airports, and more; additionally, it can act as an AI tour guide, providing accurate route planning and real-time information services for tourists. The expansion of these application scenarios showcases the enormous potential of the Xiaowen Mobile Digital Human in reducing costs, increasing efficiency, and enhancing user experience.
It is noteworthy that the Xiaowen Mobile Digital Human has achieved multiple innovations in technology. It employs edge computing technology to integrate local rendering of the digital human, microphone array algorithms, local vision algorithms, and other end-side AI, achieving efficient edge-side rendering and low-latency interaction. Moreover, the Xiaowen Mobile Digital Human supports multimodal digital human interaction, including 2.5D digital humans, 3D digital humans, and photo-based digital humans, providing users with a diverse digital human experience.
Additionally, the Xiaowen Mobile Digital Human excels in sound capabilities. It utilizes cutting-edge large model voice cloning technology, completing voice cloning in just 3 seconds. Furthermore, it has a vast AI voice library containing over 1,000 voices, supporting multiple language options, thus offering users a rich auditory experience.
Regarding the future development of the Xiaowen Mobile Digital Human, Mobvoi stated that it will continue to deepen its work on multimodal large model technology, constantly enhancing the intelligence level and interactive experience of its products. The company will also actively expand application scenarios, promoting the Xiaowen Mobile Digital Human to play an important role in more fields.