Gives Claude ears and eyes for video and audio: summarize, explain, transcribe (word-level timestamps, ~99 languages) and edit TikTok, YouTube or Instagram links and local files. Runs locally with faster-whisper and FFmpeg.
Enables Claude to analyze videos by combining local ffmpeg/OpenCV measurements (exact cut timings, frame extraction, second-by-second camera motion, flashes and audio hits) with Gemini's reading of video in motion and audio. Users can break down reference videos shot by shot, compare a reference against their own edit for concrete fixes, and inspect any video segment before publishing.
Enables Claude to analyze short-form video ads by extracting frames, audio, and transcripts, providing visual contact sheets, audio profiles, and YAMNet audio-event tags via MCP tools.
Enables Claude to create, edit, validate, and animate video projects through structured project files, including rendering frames or exports, inspecting previews, and applying themes, templates, effects, and subtitles.
Extracts YouTube transcripts and performs AI-powered video analysis for Claude Desktop, enabling transcript retrieval, quality analysis, and smart resource management.