# alibabacloud-avatar-video

alibabacloud-avatar-video is a Claude Code skill for creating talking-head videos, full-body animations, and speech via Alibaba Cloud DashScope. It supports portrait animation, character motion, and text-to-speech with voice selection.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 125 installs · ★ 300 repo stars
- Author: aliyun
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/aliyun/alibabacloud-aiops-skills/tree/HEAD/skills/aiml/avatar/alibabacloud-avatar-video/SKILL.md
- Updated: 2026-10-23
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/alibabacloud-avatar-video

## What it does

Seven built-in tools are included: LivePortrait converts a portrait photo and audio into talking-head video in two steps; EMO offers another method to animate a portrait with speech; AnimateAnyone handles full-body motion based on motion templates; T2I generates images from text prompts using Wan 2.x; I2V turns images into video, supporting text-to-image-to-video pipelines; Qwen TTS synthesizes speech with voice and tone selection by scenario; LingMou creates digital-human broadcast videos from pre-built templates.

You need Alibaba Cloud credentials (DASHSCOPE_API_KEY, OSS access keys), ffmpeg and ffprobe in PATH, and environment variables for your bucket and endpoint. Beijing and Singapore region API keys are not interchangeable—use the key for your region.

Each tool runs as a separate script in the `scripts` folder: `live_portrait.py`, `qwen_tts.py`, `text_to_image.py`, and more. Flags let you choose model, size, voice, and style; outputs save to Object Storage or download locally.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add aliyun/alibabacloud-aiops-skills --skill alibabacloud-avatar-video -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/alibabacloud-avatar-video/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/alibabacloud-avatar-video/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add aliyun/alibabacloud-aiops-skills --skill alibabacloud-avatar-video -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/alibabacloud-avatar-video/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add aliyun/alibabacloud-aiops-skills --skill alibabacloud-avatar-video -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/alibabacloud-avatar-video/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install aliyun/alibabacloud-aiops-skills skills/aiml/avatar/alibabacloud-avatar-video
```

2. **Manually: put the files in place**
- File: `.github/skills/alibabacloud-avatar-video/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add aliyun/alibabacloud-aiops-skills --skill alibabacloud-avatar-video -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/aliyun/alibabacloud-aiops-skills --path skills/aiml/avatar/alibabacloud-avatar-video
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/alibabacloud-avatar-video/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add aliyun/alibabacloud-aiops-skills --skill alibabacloud-avatar-video -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/aliyun/alibabacloud-aiops-skills/tree/HEAD/skills/aiml/avatar/alibabacloud-avatar-video/SKILL.md

## When to use it
- generate a talking-head video from a photograph and audio track
- synthesize speech from text with voice and tone options
- create an image from a text description
- animate a character with full-body motion from a template
- produce a character video from an image and text in one call

## Example prompts
- Turn a portrait photo into talking video: use LivePortrait with `--template active` for expressive motion
- Convert a speech transcript to audio with a news anchor voice using `--scene news`
- Generate a video of a character in traditional clothing from a text prompt—first text to image, then image to video

## Similar
- [ai-avatar-video](https://affpapa.org/en/nevibecode/skills/prime-skills-ai-avatar-video.md) — skill · 390700 installs
- [run-longcat-avatar-video](https://affpapa.org/en/nevibecode/skills/run-longcat-avatar-video.md) — skill · ★ 171 repo stars
- [ai-video-generation](https://affpapa.org/en/nevibecode/skills/ai-video-generation.md) — skill · 1000000 installs
- [image-to-video](https://affpapa.org/en/nevibecode/skills/image-to-video.md) — skill · 448900 installs
- [alibaba-image-models](https://affpapa.org/en/nevibecode/skills/alibaba-image-models.md) — skill · 138 installs
- [qwen-image](https://affpapa.org/en/nevibecode/skills/qwen-image.md) — skill · 122 installs

From the same set: [aliyun/alibabacloud-aiops-skills](https://affpapa.org/en/nevibecode/by/aliyun/alibabacloud-aiops-skills.md) — 66 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
