← Back to Skills Marketplace
208
Downloads
0
Stars
1
Active Installs
2
Versions
Install in OpenClaw
/install ai-video-gen-temp
Description
End-to-end AI video generation - create videos from text prompts using image generation, video synthesis, voice-over, and editing. Supports OpenAI DALL-E, Re...
README (SKILL.md)
AI Video Generation Skill
Generate complete videos from text descriptions using AI.
Capabilities
- Image Generation - DALL-E 3, Stable Diffusion, Flux
- Video Generation - LumaAI, Runway, Replicate models
- Voice-over - OpenAI TTS, ElevenLabs
- Video Editing - FFmpeg assembly, transitions, overlays
Quick Start
# Generate a complete video
python skills/ai-video-gen/generate_video.py --prompt "A sunset over mountains" --output sunset.mp4
# Just images to video
python skills/ai-video-gen/images_to_video.py --images img1.png img2.png --output result.mp4
# Add voiceover
python skills/ai-video-gen/add_voiceover.py --video input.mp4 --text "Your narration" --output final.mp4
Setup
Required API Keys
Add to your environment or .env file:
# Image Generation (pick one)
OPENAI_API_KEY=sk-... # DALL-E 3
REPLICATE_API_TOKEN=r8_... # Stable Diffusion, Flux
# Video Generation (pick one)
LUMAAI_API_KEY=luma_... # LumaAI Dream Machine
RUNWAY_API_KEY=... # Runway ML
REPLICATE_API_TOKEN=r8_... # Multiple models
# Voice (optional)
OPENAI_API_KEY=sk-... # OpenAI TTS
ELEVENLABS_API_KEY=... # ElevenLabs
# Or use FREE local options (no API needed)
Install Dependencies
pip install openai requests pillow replicate python-dotenv
FFmpeg
Already installed via winget.
Usage Examples
1. Text to Video (Full Pipeline)
python skills/ai-video-gen/generate_video.py \
--prompt "A futuristic city at night with flying cars" \
--duration 5 \
--voiceover "Welcome to the future" \
--output future_city.mp4
2. Multiple Scenes
python skills/ai-video-gen/multi_scene.py \
--scenes "Morning sunrise" "Busy city street" "Peaceful night" \
--duration 3 \
--output day_in_life.mp4
3. Image Sequence to Video
python skills/ai-video-gen/images_to_video.py \
--images frame1.png frame2.png frame3.png \
--fps 24 \
--output animation.mp4
Workflow Options
Budget Mode (FREE)
- Image: Stable Diffusion (local or free API)
- Video: Open source models
- Voice: OpenAI TTS (cheap) or free TTS
- Edit: FFmpeg
Quality Mode (Paid)
- Image: DALL-E 3 or Midjourney
- Video: Runway Gen-3 or LumaAI
- Voice: ElevenLabs
- Edit: FFmpeg + effects
Scripts Reference
generate_video.py- Main end-to-end generatorimages_to_video.py- Convert image sequence to videoadd_voiceover.py- Add narration to existing videomulti_scene.py- Create multi-scene videosedit_video.py- Apply effects, transitions, overlays
API Cost Estimates
- DALL-E 3: ~$0.04-0.08 per image
- Replicate: ~$0.01-0.10 per generation
- LumaAI: $0-0.50 per 5sec (free tier available)
- Runway: ~$0.05 per second
- OpenAI TTS: ~$0.015 per 1K characters
- ElevenLabs: ~$0.30 per 1K characters (better quality)
Examples
See examples/ folder for sample outputs and prompts.
Usage Guidance
This package contains working scripts for generating videos with third‑party APIs, but there are several inconsistencies and missing files that reduce confidence in the bundle's provenance. Before installing or running: 1) do not paste production API keys — create a throwaway key or isolated billing account for testing and rotate it afterwards; 2) inspect the code yourself (or have someone you trust do so), especially the API calls that send data to remote endpoints; 3) note SKILL.md and README reference files that are not included (.env.example, multi_scene.py, edit_video.py, examples/) and the metadata owner mismatch — treat the source as unverified; 4) be aware of cost/billing for calls to OpenAI/Runway/LumaAI/Replicate/ElevenLabs; 5) test in an isolated environment (container or VM), and if you decide to use it long-term, only enable the minimum required keys and monitor usage. If you want, I can list the exact places in code that send data to remote services and suggest minimal tests to validate behavior safely.
Capability Analysis
Type: OpenClaw Skill
Name: ai-video-gen-temp
Version: 1.0.1
The skill bundle provides a legitimate set of tools for AI video generation using OpenAI, Replicate, and LumaAI APIs. The Python scripts (generate_video.py, add_voiceover.py, images_to_video.py) use standard libraries and safely invoke FFmpeg via subprocess lists to avoid shell injection. No evidence of data exfiltration, malicious execution, or prompt injection was found.
Capability Assessment
Purpose & Capability
The scripts implement an image→video→voice pipeline and legitimately need API keys for OpenAI, Replicate, LumaAI, Runway, and ElevenLabs. However, the registry metadata claims no required environment variables or credentials, which is inconsistent with the code and SKILL.md. The _meta.json owner also differs from the registry owner id, and SKILL.md/README reference files (e.g., .env.example, multi_scene.py, edit_video.py, examples/) that are not present in the bundle — these mismatches reduce trust in the package provenance.
Instruction Scope
SKILL.md instructs the agent to use external services (OpenAI, LumaAI, Replicate, ElevenLabs) and to read environment keys from a .env file — behavior consistent with the stated purpose. But SKILL.md references scripts that are missing from the repo (multi_scene.py, edit_video.py, examples/), and the LumaAI call in generate_video.py sends a local file path string in JSON ("image": image_path) rather than uploading file contents or a public URL, which looks buggy and could leak local path information to the remote API. The runtime instructions are otherwise focused on the task and do not instruct reading unrelated system files.
Install Mechanism
There is no install spec in the registry (instruction-only), but the bundle includes a requirements.txt listing common packages (openai, replicate, requests, pillow, python-dotenv). This is proportionate to the functionality and lower risk than arbitrary binary downloads, but you must pip install dependencies before running. No external download URLs or extract/install steps are present.
Credentials
The code expects multiple API credentials (OPENAI_API_KEY, REPLICATE_API_TOKEN, LUMAAI_API_KEY, RUNWAY_API_KEY, ELEVENLABS_API_KEY). Those credentials are proportionate to a multi-provider video tool, but the registry metadata declared 'no required env vars' which is inaccurate. Because the skill will call external services, providing keys grants networked access to those services (and billing), so keys should be limited and rotated if used for testing.
Persistence & Privilege
The skill does not request persistent system privileges, does not set always:true, and does not attempt to modify other skills or global agent configs. It runs as command-line scripts and uses ordinary filesystem operations (temporary filelist.txt), which is expected for its purpose.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install ai-video-gen-temp - After installation, invoke the skill by name or use
/ai-video-gen-temp - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
- Skill name changed to "ai-video-gen-local" in documentation.
- No changes to functionality or usage instructions.
- Updated SKILL.md to reflect the new name; other content unchanged.
v1.0.0
- Initial release of AI Video Generation skill.
- Generate complete videos from text prompts using image generation, video synthesis, voice-over, and editing.
- Supports multiple models and APIs: DALL-E, Stable Diffusion, LumaAI, Runway, ElevenLabs, and Replicate.
- Includes scripts for end-to-end video creation, image-to-video conversion, voiceover addition, and multi-scene assembly.
- Provides setup instructions, API key requirements, and usage examples for various workflows.
Metadata
Frequently Asked Questions
What is Ai Video Gen Temp?
End-to-end AI video generation - create videos from text prompts using image generation, video synthesis, voice-over, and editing. Supports OpenAI DALL-E, Re... It is an AI Agent Skill for Claude Code / OpenClaw, with 208 downloads so far.
How do I install Ai Video Gen Temp?
Run "/install ai-video-gen-temp" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Ai Video Gen Temp free?
Yes, Ai Video Gen Temp is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Ai Video Gen Temp support?
Ai Video Gen Temp is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Ai Video Gen Temp?
It is built and maintained by mmyg11 (@mmyg11); the current version is v1.0.1.
More Skills