relay-video-gen
Multi-provider video generation with async polling and automatic model fallback
Best use case
relay-video-gen is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Multi-provider video generation with async polling and automatic model fallback
Teams using relay-video-gen should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/relay-video-gen/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How relay-video-gen Compares
| Feature / Agent | relay-video-gen | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Multi-provider video generation with async polling and automatic model fallback
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Relay Video Generation Multi-provider video generation with async polling and automatic model fallback. ## Quick Start ```bash uv run ~/.openclaw/skills/relay-video-gen/scripts/relay_video_gen.py \ -p "A rotating blue globe with stars in background" \ -f "globe.mp4" ``` ## Parameters | Flag | Description | Default | |------|-------------|---------| | `-p` | Video prompt (English) | Required | | `-f` | Output filename (.mp4) | Required | | `-d` | Duration in seconds (3-15) | `5` | | `-a` | Aspect ratio: `16:9`, `9:16`, `1:1` | `16:9` | | `-m` | Override model name | `kling-video` | | `-P` | Force provider | `xingjiabi` | ## Examples ```bash # 10-second vertical video for Reels/TikTok uv run ~/.openclaw/skills/relay-video-gen/scripts/relay_video_gen.py \ -p "A person typing on laptop in coffee shop, warm lighting" \ -f "coffee.mp4" -d 10 -a 9:16 # Use veo3.1 model uv run ~/.openclaw/skills/relay-video-gen/scripts/relay_video_gen.py \ -p "Ocean waves crashing on beach at sunset" \ -f "ocean.mp4" -m veo3.1-fast ``` ## Workflow 1. Submit generation request → get `task_id` 2. Poll every 5s until `completed` / `failed` (max 10 min) 3. Download video to output path 4. If model fails/saturated → auto-try next model ## Model Fallback Order Gemini (veo-3.1-generate-preview, direct Google API) → xingjiabi: kling-video → veo-3.1-fast → veo-3.1 → minimax/video-01 → grok-video-3 ## Provider Details See [references/providers.md](references/providers.md) for API formats, model status, and how to add providers.
Related Skills
videocut:自进化
字幕生成与烧录。火山引擎转录→词典纠错→审核→烧录。触发词：加字幕、生成字幕、字幕
video-transcriber
视频转写工作流，支持B站和YouTube视频。自动判断有字幕/无字幕，有字幕则获取字幕，无字幕则下载音频+whisper转写。触发场景：(1) 用户要求总结视频内容 (2) 用户要求获取视频字幕 (3) 用户要求转写视频 (4) 处理B站/YouTube视频
video-subtitles
Generate SRT subtitles from video/audio with translation support. Transcribes Hebrew (ivrit.ai) and English (whisper), translates between languages, burns subtitles into video. Use for creating captions, transcripts, or hardcoded subtitles for WhatsApp/social media.
video-script
Create video scripts and publishing materials for YouTubers/UP主. Use when user wants to prepare a video, write a script (口播稿), generate video title, description, tags, or chapter timestamps. Triggers on "写视频脚本", "视频口播稿", "video script", "prepare video", "视频发布素材", or mentions creating content for YouTube/Bilibili.
video-merge-send
合并多个分段视频为一个完整视频，并发送到飞书。使用ffmpeg拼接视频片段，支持淡入淡出转场。触发场景：用户需要合并视频片段、拼接分镜视频、视频合并后发飞书、把多个短视频合成一个、分段视频合并发送。配合 jimeng-storyboard skill 使用，完成数字人视频全流程。
video-marketing
When the user wants to plan video marketing, create video scripts, or optimize for short-form or long-form video. Also use when the user mentions "video marketing," "video script," "short-form video," "long-form video," "TikTok script," "Reels script," "YouTube script," "video hook," or "video content strategy."
video-lyrics-subtitle
Video lyrics subtitle generator — create synchronized subtitle files for music videos
video-generation
Use this skill when the user requests to generate, create, or imagine videos. Supports structured prompts and reference image for guided generation.
video-content-analyzer
下载视频并用AI分析内容 - 支持B站/抖音/YouTube等平台，提取语音内容并分析视频结构
video-caption-burner
Burn existing subtitles or captions directly into video exports so they remain visible across platforms and players. Use when a team already has captions and needs a platform-ready, subtitle-baked video for social, ads, storefronts, or review links.
showcase-video-builder
Build polished showcase and demo videos from screenshots, avatars, and text overlays using ffmpeg. Use when creating demo reels, hackathon presentations, product walkthroughs, or social media video content from static assets. Requires ffmpeg.
relay-image-gen
Multi-provider image generation with automatic priority fallback