Cloud-based media processing for video, audio, images, and documents using 86+ specialized robots. Supports video encoding (HLS, MP4, WebM), thumbnail generation, image resizing/watermarking, audio transcoding, document OCR, and speech-to-text via chainable processing steps Access via MCP server (recommended for IDE integration) or CLI; requires free Transloadit account with API credentials Build multi-step pipelines by chaining robot operations together using the "use" field; reuse pipelines as templates with dynamic variables Includes preset configurations for common formats (HLS-1080p, MP3, WebP) and batch processing via HTTP import from URLs, S3, GCS, or other cloud storage
Download YouTube videos in customizable quality and format with audio-only MP3 support. Supports six quality presets (best, 1080p, 720p, 480p, 360p, worst) and three video formats (MP4, WebM, Matroska) Audio-only downloads extract video as MP3 files for music or podcast extraction Automatically installs and uses yt-dlp for robust stream selection and merging Configurable output directory; defaults to /mnt/user-data/outputs/ with auto-generated filenames from video titles
Create animated GIFs optimized for Slack with composable animation primitives and built-in validators. Provides 15+ animation primitives (shake, bounce, spin, pulse, fade, zoom, explode, wiggle, slide, flip, morph, move, kaleidoscope) that compose freely for custom effects Includes validators for Slack's strict size limits (2MB for messages, 64KB for emoji) and dimension requirements, with optimization strategies for each constraint Offers helper utilities for GIF assembly, text rendering, color palettes, particle effects, easing functions, and frame composition Distinguishes emoji GIFs (10-15 frames, 32-48 colors, simple designs) from message GIFs (higher frame counts and color budgets) with mode-specific guidance
AI video generation and management for Sora models with character references, editing, and batch workflows. Supports video creation, editing, extension, character reference uploads, and asset downloads (video/thumbnail/spritesheet) via bundled CLI with structured prompt augmentation Defaults to sora-2 model; supports sora-2-pro for higher fidelity and larger resolutions up to 1920x1080 Handles async job polling, local multi-job queues, and official Batch API planning for offline rendering pipelines Enforces content guardrails: no real people, copyrighted material, or content unsuitable for under-18 audiences; requires OPENAI_API_KEY and Sora API access
Create Remotion videos using the Geist design system aesthetic. Use when asked to create videos, animations, or motion graphics that should follow Vercel's…
飞书妙记：妙记相关基本功能。1.查询妙记列表（按关键词/所有者/参与者/时间范围）；2.获取妙记基础信息（标题、封面、时长 等）；3.下载妙记音视频文件；4.获取妙记相关 AI 产物（总结、待办、章节）；5.上传音视频生成妙记，也支持将本地音视频文件转成纪要、逐字稿、文字稿、撰写文字等产物。遇到这类请求时，应优先使用本…
>
kling-3-0 — an installable skill for AI agents, published by agentspace-so/runcomfy-agent-skills.
Install the lark-minutes skill for your AI agent. Published on open.feishu.cn.
Create video compositions, animations, title cards, overlays, captions, voiceovers, audio-reactive visuals, and scene transitions in HyperFrames HTML. Use when…
>
>
>
>
|