魔珐星云

Overview

Xmov Nebula is an embodied intelligent 3D digital human open platform launched by Xmov Technology, providing developers with capabilities such as real-time digital human driving, video generation, and speech synthesis. The platform aims to further expand AI from “only having language understanding ability” to “having visualized bodily expression,” enabling digital humans to carry out natural interactions in voice, expressions, eye contact, gestures, and movements like real people.

It supports driving 3D digital humans through text input to generate multimodal performances, featuring low latency, low-cost deployment, and multi-terminal adaptation, and is suitable for scenarios such as intelligent customer service, AI companionship, digital teachers, service guides, and English speaking practice. For teams that need to combine large models, Agents, or intelligent terminals with digital humans, Xmov Nebula provides relatively complete open capabilities and integration methods.

Main Features

• Embodied Driving

  • Based on text input, it generates a 3D digital human’s voice, expressions, eye contact, gestures, and body movements in real time
  • Supports relatively low-latency interaction; according to the official website, driving response can reach the 500ms level
  • Can be used for real-time digital human interaction on Web, App, and multiple types of terminals

• Video Generation

  • Supports one-click generation of 3D digital human videos based on text or PPT
  • Can automatically complete content such as scenes, lighting, character performance, camera movement, and packaging
  • Suitable for producing explainer videos, teaching videos, and presentation content

• Speech Synthesis

  • Provides multilingual, multi-style voice capabilities
  • Supports emotional expression and voice cloning
  • Can be used in scenarios such as digital human broadcasting, customer service voice, and companion interaction

• Multimodal Generation and Interaction

  • Combines semantic and emotion analysis to jointly generate voice, expressions, and movements
  • Improves the naturalness and immersion of digital human expression

• Cross-terminal and Multi-system Adaptation

  • Supports terminals such as mobile phones, PCs, Pads, TVs, in-vehicle systems, and large screens
  • Compatible with mainstream systems such as Android, iOS, and HarmonyOS
  • The official website mentions compatibility with domestic Xinchuang environments

Product Pricing

Xmov Nebula adopts a points-based billing model, with different functions consuming different amounts of points:

• Real-time Driving SDK

  • Basic voice version: 0.5 points/minute
  • Pro voice version: 2 points/minute

• Video Generation

  • 720p: about 140 points/minute
  • 1080p: about 240 points/minute
  • 2K: about 880 points/minute
  • 4K: about 1340 points/minute

• Speech Synthesis

  • Basic voice version: 0.2 points/minute
  • Pro voice version: 1 point/minute

New users can usually receive trial points after registration. For actual prices and billing rules, please refer to the latest page on the official website.

Frequently Asked Questions

Who is Xmov Nebula suitable for?

It is suitable for developers, enterprise technical teams, and system integrators who need to build digital human applications, as well as product teams hoping to integrate large model capabilities into scenarios such as customer service, teaching, companionship, guidance services, and marketing.

How do you integrate Xmov Nebula?

The usual process includes: registering an account, creating an application, obtaining the AppID and AppSecret, and then integrating the real-time driving SDK or calling the video generation and speech synthesis APIs for development according to needs.

What are the typical application scenarios of Xmov Nebula?

Common scenarios include intelligent customer service, AI companionship, digital employees, AI teaching assistants, English speaking practice, business service guides, TV assistants, and embodied interaction applications combined with robots or intelligent terminals.