2025-08-14 14:04:29 +08:00
2024-05-16 17:22:43 +08:00
2025-08-14 14:04:29 +08:00
2025-08-07 16:27:33 +08:00
2025-07-22 11:20:07 +08:00
2025-03-05 18:50:24 +08:00
2024-05-24 17:41:24 +08:00
2025-06-09 17:19:46 +08:00
2025-07-22 11:20:07 +08:00

简体中文 | English

Duix Mobile 视频封面

🚀🚀🚀 Duix Mobile — The Best Real-time Interactive Digital Human Solution for Mobile Devices

📱 Cross-platform support: iOS / Android / Tablet / Automotive / VR / IoT / Large Screen Interaction, etc.

😎 What is Duix Mobile?

Duix Mobile, open-sourced by GuijiAI, is a real-time conversational digital human SDK that can be deployed on mobile phones or embedded screens.

Developers can easily integrate their own or third-party Large Language Models (LLM), Automatic Speech Recognition (ASR), and Text-to-Speech (TTS) services to quickly build digital human interfaces that can naturally converse with users.

Duix Mobile supports one-click cross-platform deployment (Android/iOS), has a low learning curve, and is suitable for various application scenarios such as intelligent customer service, virtual doctors, virtual lawyers, virtual companionship, and virtual teaching.

Start building your own interactive digital human now and significantly boost your product performance!

🤩 Application Scenarios

  • Duix Mobile supports various practical application scenarios across Android/iOS/Pad/large screen devices;
  • Significantly enhance your product performance and boost your revenue levels.

🥳 Advantages

  • Realistic Digital Human Experience: Natural presentation of facial expressions, tone, and emotional resonance, creating "human-like" AI conversations.
  • Streaming Audio Support: Synthesize and speak simultaneously, supports interruption and barge-in, making digital humans not only talk but also behave more "human-like".
  • Ultimate Response Speed: Digital human response latency under 120ms (tested on Snapdragon® 8 Gen 2 SoC), delivering millisecond-level smooth interaction experience.
  • Cost-Friendly, Deploy Anywhere: Lightweight operation, extremely low resource consumption, easily adaptable to phones, tablets, smart screens, and other terminals.
  • Resilient in Weak Network Environments: Core processing completed locally, minimal network dependency, especially suitable for scenarios requiring high stability like finance, government, and legal sectors.
  • Comprehensive Industry Adaptation: Modular design, supports rapid customization, easily create industry-specific digital human solutions.

📑 Development Documentation

💚 Real Deployment Cases

See on Bilibili:

Public Digital Human Downloads

  • Below are 8 public digital humans provided by Duix, available for download and integration.
Model 1
Download
Model 2
Download
Model 3
Download
Model 8
Download
Model 5
Download
Model 6
Download
Model 7
Download
Model 4
Download

🤗 How to Customize Private Digital Humans?

  • Having deployment issues? Want to customize private digital humans?
  • Please send an email to: amos.young@duix.com
  • Or add our enterprise WeChat:
Enterprise WeChat

🙌 Frequently Asked Questions

Can I integrate my own Large Language Model (LLM), Speech Recognition (ASR), and Text-to-Speech (TTS)?

Yes, you can integrate Duix-Mobile's digital humans with your own LLM, ASR, and TTS.

Does it support "lip synchronization"?

Yes, it does.

Does it support "multilingual subtitles"?

Yes, it does.

How do I create custom digital humans?

We provide 8 public digital humans. For additional customization, please contact the enterprise WeChat above.

Usually, recording a 15-second to 2-minute video is sufficient to complete the customization process, making it simple and convenient.

Is streaming audio supported?

Yes, streaming audio was released in the July 17, 2025 update.

Are callbacks provided for digital human voice start and end?

Yes, we provide documentation for voice start and end callbacks.

💡 Version Roadmap

  • Streaming audio capability, completed by July 16, 2025
  • Algorithm response optimization, expected by August 30, 2025
Description
镜像至GitHub:/GuijiAI/duix.ai.git
Readme 603 MiB
Languages
C++ 73.5%
C 14.2%
Objective-C 10.2%
Java 0.8%
CMake 0.6%
Other 0.6%