# HenGem数字人

**Repository Path**: KingRain.NET/HenGem

## Basic Information

- **Project Name**: HenGem数字人
- **Description**: 支持批量处理中英、批量小语种处理、API密钥管理、IP管理、系统代理、使用说明等，另外新增本地模型和公共库模型，本地模型只能用户自己使用，公共库可以多用户使用。
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: dev
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 41
- **Created**: 2025-06-12
- **Last Updated**: 2025-06-12

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# HeyGem: Free Open-Source Alternative to HeyGen

> Custom backend repository: https://gitee.com/Martinkeep/digital-human-public-library

## System Requirements

**Recommended Configuration**
- **Processor**: 13th Gen Intel Core i5-13400F
- **Memory**: 32GB
- **Graphics Card**: RTX 4070 (NVIDIA cards recommended)
- **Storage**: C drive > 100GB (if insufficient, select a new folder after installing Docker), D drive > 30GB
- **Software Dependencies**: Node 18, Docker Desktop, Git

## 预览
<img src="images/image100.png" width="300" />

<img src="images/image101.png" width="300" />

<img src="images/image102.png" width="300" />

<img src="images/image103.png" width="300" />

<img src="images/image107.jpg" width="140" />

<img src="images/image108.png" width="300" />

<img src="images/image109.png" width="300" />

<img src="images/image110.png" width="300" />

<img src="images/image111.png" width="300" />

<img src="images/image112.png" width="300" />

## Quick Deployment Guide

### 1. Install Required Software

#### Install Node.js
1. Visit [Node.js official website](https://nodejs.org/en/download) to download the installer
2. Follow the prompts to complete installation

#### Install Docker Desktop
1. Before installing Docker Desktop for the first time, run these commands in Command Prompt (CMD):
   ```bash
   # Install WSL (may fail due to network issues, try multiple times, may require computer restart)
   wsl --install

   # Update WSL
   wsl --update
   ```

2. Visit [Docker's official website](https://www.docker.com/) to download the installer
3. Double-click to run Docker
4. Accept the agreement on first run, then skip login

> **Note**: If you encounter WSL-related errors during startup, run `wsl --install` in the CMD window, then restart your computer.

> **Tip**: If your C drive has less than 100GB available, you can select a disk folder with more than 100GB of free space in the settings after installing Docker.

#### Install Git
1. Visit [Git's official website](https://git-scm.com/downloads/win) to download the installer
2. Follow the prompts to complete installation

### 2. Server Deployment: Dual-Channel Docker Solution

Choose one of the following methods based on your network conditions:

#### Method 1: Manual Image Pulling

##### China Accelerated Channel (No VPN required)
```bash
# Speech Recognition Engine
docker pull crpi-87t8jkvf79rj7hal.cn-huhehaote.personal.cr.aliyuncs.com/modelers_park/fun-asr:latest

# Speech Synthesis Module
docker pull crpi-87t8jkvf79rj7hal.cn-huhehaote.personal.cr.aliyuncs.com/modelers_park/fish-speech-ziming:latest

# Core AI Engine
docker pull crpi-87t8jkvf79rj7hal.cn-huhehaote.personal.cr.aliyuncs.com/modelers_park/heygem.ai:latest
```

After successful pulling, create a `docker-compose.yml` file with the following content:

```yaml
networks:
  ai_network:
    driver: bridge

services:
  heygem-tts:
    image: crpi-87t8jkvf79rj7hal.cn-huhehaote.personal.cr.aliyuncs.com/modelers_park/fish-speech-ziming
    container_name: heygem-tts
    restart: always
    runtime: nvidia
    environment:
      - NVIDIA_VISIBLE_DEVICES=0
      - NVIDIA_DRIVER_CAPABILITIES=compute,graphics,utility,video,display
    ports:
      - '18180:8080'
    volumes:
      - d:/heygem_data/voice/data:/code/data
    command: /bin/bash -c "/opt/conda/envs/python310/bin/python3 tools/api_server.py --listen 0.0.0.0:8080"
    networks:
      - ai_network
  heygem-asr:
    image: crpi-87t8jkvf79rj7hal.cn-huhehaote.personal.cr.aliyuncs.com/modelers_park/fun-asr
    container_name: heygem-asr
    restart: always
    runtime: nvidia
    privileged: true
    working_dir: /workspace/FunASR/runtime
    ports:
      - '10095:10095'
    command: sh /run.sh
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    networks:
      - ai_network
  heygem-f2f:
    image: crpi-87t8jkvf79rj7hal.cn-huhehaote.personal.cr.aliyuncs.com/modelers_park/heygem.ai
    container_name: heygem-f2f
    restart: always
    runtime: nvidia
    privileged: true
    volumes:
      - d:/heygem_data/face2face:/code/data
    environment:
      - PYTORCH_CUDA_ALLOC_CONF=max_split_size_mb:512
    deploy:
      resources:
        reservations:
          devices:
            - capabilities: [gpu]
    shm_size: '8g'
    ports:
      - '8383:8383'
    command: python /code/app_local.py
    networks:
      - ai_network
```

##### International Channel (VPN required)
```bash
docker pull guiji2025/fun-asr
docker pull guiji2025/fish-speech-ziming
docker pull guiji2025/heygem.ai
```

After successful pulling, create a `docker-compose.yml` file with the following content:

```yaml
networks:
  ai_network:
    driver: bridge

services:
  heygem-tts:
    image: guiji2025/fish-speech-ziming
    container_name: heygem-tts
    restart: always
    runtime: nvidia
    environment:
      - NVIDIA_VISIBLE_DEVICES=0
      - NVIDIA_DRIVER_CAPABILITIES=compute,graphics,utility,video,display
    ports:
      - '18180:8080'
    volumes:
      - d:/heygem_data/voice/data:/code/data
    command: /bin/bash -c "/opt/conda/envs/python310/bin/python3 tools/api_server.py --listen 0.0.0.0:8080"
    networks:
      - ai_network
  heygem-asr:
    image: guiji2025/fun-asr
    container_name: heygem-asr
    restart: always
    runtime: nvidia
    privileged: true
    working_dir: /workspace/FunASR/runtime
    ports:
      - '10095:10095'
    command: sh /run.sh
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    networks:
      - ai_network
  heygem-f2f:
    image: guiji2025/heygem.ai
    container_name: heygem-f2f
    restart: always
    runtime: nvidia
    privileged: true
    volumes:
      - d:/heygem_data/face2face:/code/data
    environment:
      - PYTORCH_CUDA_ALLOC_CONF=max_split_size_mb:512
    deploy:
      resources:
        reservations:
          devices:
            - capabilities: [gpu]
    shm_size: '8g'
    ports:
      - '8383:8383'
    command: python /code/app_local.py
    networks:
      - ai_network
```

#### Method 2: One-Click Automated Deployment (Recommended for Beginners)

1. Clone the repository (skip if network issues occur):
   ```bash
   git clone https://github.com/GuijiAI/HeyGem.ai.git
   ```

2. If you can't clone the repository, manually create a `docker-compose.yml` file with the same content as the International Channel version

3. Start the container cluster:
   ```bash
   # Navigate to the directory containing docker-compose.yml
   cd HeyGem.ai/deploy

   # Launch services
   docker-compose up -d
   ```

After execution, you should see three running services in Docker, indicating successful server deployment.

### 3. Client Installation

1. Download the official installation package: https://github.com/GuijiAI/HeyGem.ai/releases
2. Double-click to install `HeyGem-x.x.x-setup.exe`
3. Launch and start customizing your digital human

> **Note**: Currently only Chinese and English text are supported

## Developer Information

If you're a developer looking to customize additional features (such as batch processing, support for other languages, etc.), you can pull the frontend code:

```bash
git clone https://github.com/GuijiAI/HeyGem.ai.git
```

The frontend is developed using Vue3 + Electron framework, allowing for custom feature development.

## Related Resources

- Video tutorial: https://mp.weixin.qq.com/s/uBmGFt4XpjdTuVs5O8x99A

💡 If you find this project helpful, please show your support with a Star!