🎬 Video Generator Skill

Automated text-to-video generation system that transforms text scripts into professional short videos with AI-powered voiceover, precise timing, and cyber-wireframe visuals.

Cost: ~$0.003 per 15-second video | License: MIT | Package: openclaw-video-generator

📦 Package Information

Verification:

npm info openclaw-video-generator version repository.url
# Expected: 1.6.2 and https://github.com/ZhenRobotics/openclaw-video-generator

🔐 Provider Setup (Choose ONE)

This tool supports 4 alternative TTS/ASR providers. You only need ONE configured:

Option 1: OpenAI (Recommended)

export OPENAI_API_KEY="sk-..."

• - Pros: Best quality, simple setup
• Cost: ~$0.003 per 15s video

Option 2: Azure

export AZURE_SPEECH_KEY="..."
export AZURE_SPEECH_REGION="eastasia"

• - Pros: Enterprise reliability
• Cost: Similar to OpenAI

Option 3: Aliyun (阿里云)

export ALIYUN_ACCESS_KEY_ID="..."
export ALIYUN_ACCESS_KEY_SECRET="..."
export ALIYUN_APP_KEY="..."

• - Pros: China connectivity, Chinese voices
• Cost: ~¥0.02 per 15s video

Option 4: Tencent (腾讯云)

export TENCENT_SECRET_ID="..."
export TENCENT_SECRET_KEY="..."
export TENCENT_APP_ID="..."

• - Pros: China connectivity
• Cost: ~¥0.02 per 15s video

Why multiple providers? Fallback support for network restrictions, regional preferences, and cost optimization.

🚀 Quick Start

Prerequisites

Installation

Option 1: npm Global Install
CODEBLOCK6

Option 2: From Source
CODEBLOCK7

First Video

cd ~/openclaw-video-generator
cat > test.txt << 'EOF'
AI makes development easier
Saving time and boosting efficiency
EOF

./scripts/script-to-video.sh test.txt --voice nova --speed 1.15
# Output: out/test.mp4

💻 Agent Usage

When to Use

Standard Command

With Background Video

Example Flow

User: "Generate video: AI makes development easier"

Agent:
CODEBLOCK11

Guidelines

Do:

• - Verify project exists before running
• Check .env configuration
• Show output file location

Don't:

• - Clone without user confirmation
• Hardcode API keys in commands
• Create new Remotion projects

🎯 Core Features

• - Multi-Provider TTS: OpenAI, Azure, Aliyun, Tencent with auto-fallback
• Timestamp Extraction: Precise speech-to-text segmentation
• Scene Detection: 6 intelligent scene types with auto-styling
• Video Rendering: Remotion with cyber-wireframe aesthetics
• Background Videos: Custom backgrounds with opacity control
• Local Processing: Video rendering happens on your machine

⚙️ Configuration

TTS Voices

OpenAI:

• - nova (recommended), alloy, echo, INLINECODE9

Azure:

• - zh-CN-XiaoxiaoNeural, INLINECODE11

Speech Speed

Background Video

• - --bg-video <path> - Video file
• INLINECODE13 - Transparency
• INLINECODE14 - Text overlay

Recommended:

📊 Video Specs

• - Resolution: 1080 x 1920 (vertical)
• Frame Rate: 30 fps
• Format: MP4 (H.264 + AAC)
• Style: Cyber-wireframe with neon colors
• Duration: Auto-calculated

🎨 Scene Types

💰 Cost

Per 15-second video: ~$0.003 (< 1 cent)

• - TTS: ~$0.001
• Whisper: ~$0.0015
• Rendering: Free (local)

🔧 Troubleshooting

Project Not Found

API Key Error

Provider Test

cd ~/openclaw-video-generator && ./scripts/test-providers.sh

🔒 Privacy

Local Processing:

• - Video rendering
• Scene orchestration
• File management

Cloud Processing (via configured provider):

• - Text-to-Speech (text sent to API)
• Speech recognition (audio sent to API)

API keys are stored in .env file (600 permissions, never committed to git).

📚 Documentation

• - npm: https://www.npmjs.com/package/openclaw-video-generator
• GitHub: https://github.com/ZhenRobotics/openclaw-video-generator
• Issues: https://github.com/ZhenRobotics/openclaw-video-generator/issues

📊 Tech Stack

Remotion · OpenAI · Azure · Aliyun · Tencent · TypeScript · Node.js · FFmpeg

🆕 Version History

v1.6.2 (2026-03-25) - Current

• - Chinese TTS integration (Aliyun)
• Dual subtitle styles
• Medical content examples

v1.6.0 (2026-03-18)

• - Premium styles system
• Poster generator
• Design tokens

v1.2.0 (2026-03-07)

• - Background video support
• Multi-provider architecture
• Auto-fallback

v1.0.0 (2026-03-03)

• - Initial release