flyworks-avatar-video

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Avatar Video Generation Skill

Avatar视频生成技能

This skill allows you to generate videos using Flyworks (a.k.a HiFly 飞影数字人) Digital Humans. Available features:

Public Avatar Video: Create video from text or audio using pre-made highly realistic avatars.
Talking Photo: Create a "talking photo" video from a single image and text/audio.
Voice Cloning: Clone a voice from an audio sample to use in TTS.

For detailed documentation, see the references/ folder:

authentication.md - API token setup
avatars.md - Working with avatars
voices.md - Voice selection and cloning
video-generation.md - Video creation workflow

该技能支持使用Flyworks（又名HiFly 飞影数字人）数字人生成视频。可用功能：

公共虚拟形象视频：使用预先制作的高度逼真虚拟形象，通过文本或音频生成视频。
会说话的照片：从单张图片和文本/音频创建“会说话的照片”视频。
语音克隆：从音频样本中克隆语音，用于TTS。

如需详细文档，请查看references/文件夹：

authentication.md - API令牌设置
avatars.md - 虚拟形象使用指南
voices.md - 语音选择与克隆
video-generation.md - 视频创建流程

API Token & Limitations

API令牌与限制

This skill works with a default free-tier token, but it has limitations:

Watermark: Generated videos will have a watermark.
Duration Limit: Videos are limited to 30 seconds.

To remove limitations:

Register at hifly.cc or flyworks.ai.
Get your API key from User Settings.

Set the environment variable:

export HIFLY_API_TOKEN="your_token_here"

该技能使用默认的免费层级令牌，但存在以下限制：

水印：生成的视频将带有水印。
时长限制：视频最长为30秒。

如需解除限制：

在hifly.cc或flyworks.ai注册账号。
从用户设置获取API密钥。

设置环境变量：

export HIFLY_API_TOKEN="your_token_here"

Tools

工具

scripts/hifly_client.py

scripts/hifly_client.py

The main entry point for all operations.

所有操作的主入口。

Usage

使用方法

bash

undefined

bash

undefined

List available public avatars

列出可用的公共虚拟形象

python scripts/hifly_client.py list_public_avatars

List available public voices

列出可用的公共语音

python scripts/hifly_client.py list_public_voices

Create a video with a public avatar (TTS)

使用公共虚拟形象创建视频（TTS）

python scripts/hifly_client.py create_video --type tts --text "Hello world" --avatar "avatar_id_or_alias" --voice "voice_id_or_alias"

Create a video with a public avatar (Audio URL or File)

使用公共虚拟形象创建视频（音频URL或文件）

python scripts/hifly_client.py create_video --audio "https://... or path/to/audio.mp3" --avatar "avatar_id_or_alias"

Create a talked photo video using bundled assets

使用内置资源创建会说话的照片视频

python scripts/hifly_client.py create_talking_photo --image assets/avatar.png --title "Bundled Avatar"

Clone a voice using bundled assets

使用内置资源克隆语音

python scripts/hifly_client.py clone_voice --audio assets/voice.MP3 --title "Bundled Voice"

Check status of generated tasks

检查生成任务的状态

python scripts/hifly_client.py check_task --id "TASK_ID"

Manage local aliases (saved in memory.json)

管理本地别名（保存于memory.json）

python scripts/hifly_client.py manage_memory add my_avatar "av_12345" python scripts/hifly_client.py manage_memory list

undefined

python scripts/hifly_client.py manage_memory add my_avatar "av_12345" python scripts/hifly_client.py manage_memory list

undefined

Examples

示例

1. Create a simple greeting video

1. 创建简单问候视频

bash

undefined

bash

undefined

First find a voice and avatar

先找到合适的语音和虚拟形象

python scripts/hifly_client.py list_public_avatars python scripts/hifly_client.py list_public_voices

Generate

生成视频

python scripts/hifly_client.py create_video --type tts --text "Welcome to our service." --avatar "av_public_01" --voice "voice_public_01"

undefined

python scripts/hifly_client.py create_video --type tts --text "Welcome to our service." --avatar "av_public_01" --voice "voice_public_01"

undefined

2. Use a custom talking photo

2. 使用自定义会说话的照片

bash

undefined

bash

undefined

Create the avatar from an image URL

通过图片URL创建虚拟形象

python scripts/hifly_client.py create_talking_photo --image "https://mysite.com/photo.jpg" --title "CEO Photo"

Output will give you an Avatar ID, e.g., av_custom_99

输出会给出虚拟形象ID，例如av_custom_99

Save it to memory

将其保存到本地记忆

python scripts/hifly_client.py manage_memory add ceo av_custom_99

Generate video using the new avatar

使用新虚拟形象生成视频

python scripts/hifly_client.py create_video --type tts --text "Here is the quarterly report." --avatar ceo --voice "voice_public_01"

undefined

python scripts/hifly_client.py create_video --type tts --text "Here is the quarterly report." --avatar ceo --voice "voice_public_01"

undefined

Agent Behavior Guidelines

Agent行为准则

When assisting users with video generation, follow these guidelines:

协助用户生成视频时，请遵循以下准则：

Voice Selection Required

语音选择要求

Video generation requires both text AND a voice. If the user provides text but no voice:

Check local memory first: Run
```
manage_memory list
```
to see if the user has saved any voice aliases.
Ask the user to choose:
- "I see you want to create a video with the text '[text]'. Which voice would you like to use?"
- If they have saved voices: "You have these saved voices: [list]. Or would you prefer a public voice?"
- If no saved voices: "Would you like to use a public voice, or clone your own voice from an audio sample first?"

Help them select:

To see public voices:
```
list_public_voices
```

To clone a voice:

clone_voice --audio [file] --title [name]

视频生成需要同时提供文本和语音。 如果用户仅提供文本未指定语音：

先检查本地记忆：运行
```
manage_memory list
```
查看用户是否已保存语音别名。
请用户选择：
- “我了解您想使用文本‘[text]’创建视频。请问您想使用哪种语音？”
- 如果用户有保存的语音：“您已保存以下语音：[列表]。或者您想使用公共语音？”
- 如果没有保存的语音：“您想使用公共语音，还是先从音频样本克隆自己的语音？”

协助用户选择：

查看公共语音：
```
list_public_voices
```

克隆语音：

clone_voice --audio [file] --title [name]

Complete Workflow Example

完整流程示例

For a prompt like "Create a talking photo video from my photo saying 'this is my AI twin'":

Ask: "Which voice would you like for your AI twin? You can use a public voice or clone your own."
If they want to clone: Help them with
```
clone_voice
```

Create the talking photo with both text and voice:

bash

python scripts/hifly_client.py create_talking_photo \
  --image user_photo.jpg \
  --text "this is my AI twin" \
  --voice SELECTED_VOICE_ID \
  --title "My AI Twin"

对于类似“用我的照片创建一个会说‘this is my AI twin’的会说话的照片视频”的请求：

询问：“您想为AI分身使用哪种语音？可以选择公共语音或克隆自己的语音。”
如果用户想要克隆：协助执行
```
clone_voice
```
命令

使用文本和语音创建会说话的照片：

bash

python scripts/hifly_client.py create_talking_photo \
  --image user_photo.jpg \
  --text "this is my AI twin" \
  --voice SELECTED_VOICE_ID \
  --title "My AI Twin"

Saving for Later

保存以备后用

After creating avatars or cloning voices, offer to save them:

bash

python scripts/hifly_client.py manage_memory add my_avatar AVATAR_ID --kind avatar
python scripts/hifly_client.py manage_memory add my_voice VOICE_ID --kind voice

创建虚拟形象或克隆语音后，可提议保存：

bash

python scripts/hifly_client.py manage_memory add my_avatar AVATAR_ID --kind avatar
python scripts/hifly_client.py manage_memory add my_voice VOICE_ID --kind voice