video▌

Category: service

Category: provider

Analyze short-form videos with Gemini AI to extract hooks, content structure, delivery style, and CTA strategies.

Generate professional AI voiceovers for Remotion videos using ElevenLabs API.

Domain-specific best practices and patterns for building videos with Remotion and React. \n \n Covers 28 rule files spanning animations, assets, audio, compositions, captions, charts, 3D content, and transitions \n Includes utilities for media metadata extraction (video/audio duration, dimensions, frame extraction) via Mediabunny \n Provides patterns for text measurement, DOM node sizing, font loading, TailwindCSS integration, and timing/easing functions \n Addresses common workflows like captio

Use this skills whenever you are dealing with Remotion code to obtain the domain-specific knowledge.

When a user reports a video not working, we should download the URL and put it as the src in packages/example/src/NewVideo.tsx . \n Then, in packages/example , we should run bunx remotion render NewVideo --log=verbose .

Download video and audio from URLs using yt-dlp directly. No wrapper scripts needed.

Extract, transcribe, and summarize Douyin videos with local whisper.cpp processing. \n \n Handles both short ( v.douyin.com ) and direct Douyin URLs by parsing video IDs and intercepting audio via browser JavaScript \n Uses ffmpeg to convert audio to WAV and whisper.cpp for local Chinese transcription, with automatic Metal GPU acceleration on Apple Silicon \n Generates structured summaries with core points, details, and one-line takeaways in markdown format \n Optional Feishu (Lark) document syn

Generate complete videos from a text prompt. Describe what you want and the AI handles script writing, avatar selection, visuals, voiceover, pacing, and captions automatically.