Downloads a video link, samples frames from it, and transcribes the speech with Groq Whisper so an agent can answer questions about what the video shows; long audio is split into 15-minute windows to stay under the upload limit, and frames still come back without a key, which only the transcript needs. Needs ffmpeg, ffprobe and yt-dlp on PATH.
Install
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:dungcsnd1133/dsh-video-watch
Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time — pnpm blocks those until you allow them, so an install can stop with ERR_PNPM_GIT_DEP_PREPARE_NOT_ALLOWED or ERR_PNPM_IGNORED_BUILDS; dsh prints the exact key to add under allowBuilds in your profile’s pnpm-workspace.yaml, and the install works on the next run. Allowing a build is a trust decision: only install sources you trust, and pin a commit (github:owner/repo#sha).
README
Một tool DSH: watch_video.
Nhận link YouTube, TikTok, Facebook, Instagram, X, hoặc file mp4. Tải video, tách 8 đến 24 khung hình, và chép lời bằng Groq Whisper nếu máy có GROQ_API_KEY.
Máy chạy DSH cần ffmpeg, ffprobe, và yt-dlp trên PATH.
Cài
dsh plugin --profile web add ./dsh-video-watch
dsh web
Profile superagent dùng cùng lệnh, đổi --profile web thành --profile superagent.
API key để chép lời
Tạo key tại Groq Console, rồi đặt biến GROQ_API_KEY. Không có key thì tool vẫn trả khung hình và ghi rõ là chưa chép lời.
Lời nói gửi POST https://api.groq.com/openai/v1/audio/transcriptions, model
whisper-large-v3-turbo (mặc định). Đổi model bằng biến GROQ_STT_MODEL — ví dụ
whisper-large-v3 nếu cần độ chính xác cao hơn trên audio khó; nó đắt hơn khoảng ba lần
mỗi giờ và chậm hơn, nên chỉ dùng khi thật sự cần.
Âm thanh dài hơn 24 MB (giới hạn một request của Groq ở gói miễn phí) được cắt thành các cửa sổ 15 phút rồi ghép lại — một video hội thoại dài sẽ vượt giới hạn đó nếu gửi nguyên khối.
Links
More in this category
DayuanJiang/next-ai-draw-io#dsh-plugin★ 36802
Draws draw.io diagrams in DeepSeek Harness through the next-ai-drawio MCP server: the link in the reply opens a live preview in the right sidebar, you can edit the diagram by hand, and each AI change is a version you can restore. Node.js 18+; npx downloads the MCP server on first use.
Tencent/WeKnora#dsh-weknora★ 36302
Four read-only tools over a WeKnora knowledge base: list knowledge bases, hybrid passage search, reassemble one document's chunks in order, and WeKnora's own cited RAG or ReAct-agent answer with a resumable session id.
superdesigndev/treg★ 7042
Tool catalog for agents: search ~2,600 external endpoints (SEO and SERP, backlinks, social, people and company enrichment, ad libraries, scraping) by the task you want done, read each one's parameters and per-call price, then call it with the credential injected server-side. Ships the skill plus an MCP row that stays disabled until TREG_TOKEN is set.
T-Auto/dsh-ops★ 5074
Provides bash, PowerShell 7, and high-performance Rust tools for DSH on Windows to reduce token usage.
sixtysevenlf/dsh-blender-plugin★ 1575
Lets a DSH agent drive a local Blender over a direct TCP channel with 15 tools: viewport frames, custom-angle renders, Python execution, headless and job offload, transaction rollback, and a planning layer of 228 ops across 34 families.
TencentCloudBase/CloudBase-AI-Toolkit#dsh-plugin★ 1155
Tencent CloudBase backend for DeepSeek Harness — scaffold and deploy full-stack apps from chat, render query results as table cards with paging, sorting and CSV export, preview a deployment on its domain, and call the CloudBase MCP toolset (`mcp__cloudbase__*`) with device-code login.
Community comments
Comments are public GitHub Discussions. Loading them connects to GitHub and Giscus; a GitHub account is required to post.