maxgent

Generates AI videos using Veo and Sora models, supporting text-to-video and image-guided video creation with customizable parameters.

Extracts audio from video files with customizable format, quality, and time range settings using FFmpeg.

Trims and processes video segments with flexible options for compression, audio control, and output format selection.

Transcickribes audio/video files into text text with word-timestamps using WhisperXper, supporting multiple languages output formats. Human.

Automates browser interactions, maintaining page state to navigate websites, fill forms, take screenshots, extract data, and perform web testing workflows.

Merges multiple video files into a single video using FFmpeg, handling resolution and codec compatibility automatically.

Generates AI images with customizable models, styles, and editing options, supporting various image creation scenarios.

Extracts and transforms successful experiences from the current conversation into reusable Claude Code Skills.

Analyzes and understands multimedia content (images, videos, audio) using AI, extracting insights, transcribing, and answering questions.

Streamlines AI plugin development with pre-configured templates, code generation, and deployment tools for rapid Claude AI integration.