# ai-video-gen

ai-video-gen produces full AI videos from text prompts by orchestrating image generators, video synthesis engines, and FFmpeg.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 155 installs · ★ 675 repo stars
- Author: sundial-org
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/sundial-org/awesome-openclaw-skills/tree/HEAD/skills/ai-video-gen/SKILL.md
- Updated: 2026-03-07
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/sundial-org-ai-video-gen

## What it does

This tool stitches together the whole pipeline from prompt to finished clip. Dedicated Python scripts handle specific stages: `generate_video.py` orchestrates the entire text-to-video workflow, `images_to_video.py` stitches still frames into a video track, `add_voiceover.py` adds narration, and `multi_scene.py` merges multiple prompts into one cut.

The underlying processes rely on third-party providers. Image creation hooks into DALL-E 3, Stable Diffusion, or Flux. Motion synthesis goes through Runway, LumaAI Dream Machine, or Replicate, while speech uses OpenAI TTS or ElevenLabs. Assembling final transitions and overlays relies on FFmpeg.

Running these scripts requires active API tokens configured in your `.env` file, alongside an existing FFmpeg installation on your machine.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add sundial-org/awesome-openclaw-skills --skill ai-video-gen -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add sundial-org/awesome-openclaw-skills --skill ai-video-gen -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add sundial-org/awesome-openclaw-skills --skill ai-video-gen -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install sundial-org/awesome-openclaw-skills skills/ai-video-gen
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add sundial-org/awesome-openclaw-skills --skill ai-video-gen -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/sundial-org/awesome-openclaw-skills --path skills/ai-video-gen
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add sundial-org/awesome-openclaw-skills --skill ai-video-gen -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/sundial-org/awesome-openclaw-skills/tree/HEAD/skills/ai-video-gen/SKILL.md

## When to use it
- produce a complete narrated video directly from a text prompt
- compile a sequence of still frames into an MP4 file
- chain several distinct scenes into a continuous clip
- attach generated speech narration to an existing video

## Example prompts
- Run generate_video.py with the prompt "Futuristic city at night" and save it to future.mp4
- Convert frame1.png, frame2.png, and frame3.png into a video at 24 fps using images_to_video.py
- Attach spoken narration to input.mp4 with add_voiceover.py

## Similar
- [text-to-video](https://affpapa.org/en/nevibecode/skills/text-to-video.md) — skill · 156 installs
- [video-generation-gateways](https://affpapa.org/en/nevibecode/skills/video-generation-gateways.md) — skill · 149 installs
- [video-gen](https://affpapa.org/en/nevibecode/skills/video-gen.md) — skill · 339 installs
- [founder-product-video](https://affpapa.org/en/nevibecode/skills/founder-product-video.md) — skill · 1700 installs
- [muapi-jewelry-product-video](https://affpapa.org/en/nevibecode/skills/muapi-jewelry-product-video.md) — skill · 671 installs
- [video-producer-agent](https://affpapa.org/en/nevibecode/skills/video-producer-agent.md) — skill · 1 install

## Other versions with the same name
- [ai-video-gen · calesthio](https://affpapa.org/en/nevibecode/skills/ai-video-gen.md) — 1400 installs
- [ai-video-gen · calesthio](https://affpapa.org/en/nevibecode/skills/calesthio-ai-video-gen.md) — ★ 78316 repo stars

From the same set: [sundial-org/awesome-openclaw-skills](https://affpapa.org/en/nevibecode/by/sundial-org/awesome-openclaw-skills.md) — 37 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
