video▌

Translate natural language video editing requests into ready-to-run FFmpeg commands. \n \n Supports 15+ operations: cut/trim, format conversion, aspect ratio changes, resolution scaling, compression, audio extraction, speed adjustment, GIF creation, rotation, watermarking, subtitle burning, and video merging \n Handles common aspect ratios (16:9, 4:3, 1:1, 9:16, 21:9) with automatic letterboxing and standard resolutions (4K, 1080p, 720p, 480p, 360p) \n Includes time format flexibility (HH:MM:SS,

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

$23

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.

FFmpeg automation for cutting, trimming, concatenating, and exporting videos with audio mixing and platform optimization. \n \n Supports cutting, trimming, concatenation, transitions, effects, and color grading through FFmpeg CLI automation \n Handles audio mixing, normalization, and synchronization; subtitle burning and soft-subtitle handling \n Provides platform-specific export presets for YouTube, Instagram, Twitter, TikTok, and web delivery with bitrate and resolution optimization \n Batch p

Generate AI videos from text prompts. Supports multiple providers (VEO 3.1, Kling, Sora, Runway, Seedance), configurable aspect ratios, and optional reference images for image-to-video generation.

Create polished, performant animations and micro-interactions.

Edit videos locally by running ffmpeg/ffprobe directly. No wrapper scripts needed.

Extract individual frames or thumbnails from videos at specified timestamps. \n \n Single command extracts frames at any timestamp or defaults to the first frame \n Supports both JPG (for quick sharing) and PNG (for crisp UI frames) output formats \n Requires ffmpeg binary; installation via Homebrew included \n

Convert still images to animated videos via inference.sh CLI.