aixlb/dsh-bcc

Turns a video into a script, storyboard or style guide inside DSH, with the plugin owning ffmpeg cut detection, keyframes and document export while analysis uses the session's existing model.

The plugin owns the video plumbing: ffmpeg cut detection, keyframe extraction, and export to docx, xlsx or html. Analysis uses whatever model the current DSH session already has, so there is no separate provider settings page and no bundled API key to manage. The result is a script, a storyboard or a style guide derived from the footage, with a web panel and DSH skills shipped alongside the tools.

Vision & Multimodal ★ 0 updated 2026-10-18
View on GitHub ↗

Install

npx @deepseek-ai/dsh plugin --profile web add github:aixlb/dsh-bcc

Copied verbatim from the README's install line for the plugin. The repository is the independently installable DSH plugin from the same project as the bcc desktop application and CLI; you do not need those to install or run it. ffmpeg and ffprobe must be on PATH for the video smoke test, or set BCC_FFMPEG_PATH and the companion variables.

Compatibility

Version 0.1.7 targets DSH 0.2.0-rc.2 as npm latest and 0.2.1-rc.2 as npm next, checked 2026-10-18, with both engines.dsh and the DSH tools peer range declared. Use Node.js 22.19 or newer in the 22.x series, or Node.js 24. The plugin keeps its video-processing modules locally so a GitHub install does not depend on a checkout.

Details

Alternatives

maxwell-feng/dsh-tesseract-ocr · kittcat-lab/dsh-kitt-voice · kaixinbaba/dsh-vision-recognizer

More plugins in Vision & Multimodal

Browse more in Vision & Multimodal

Guides for Vision & Multimodal plugins