Turn a script into a narrated explainer video: text-card slides by default (fast and exact for tutorials) or AI-generated footage per segment (needs AGNES_API_KEY); 14 online neural Chinese voices plus 3 offline Windows voices, with a one-command sample pack for picking a voice by ear. Requires ffmpeg, and the bundled video-remix skill copied to <workspace>/.dsh/skills/video-remix with npm install run there for the online voices.
Install
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:fj7937290-sys/dsh-video-remix
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
This plugin publishes its README in Chinese only.
把文案变成带配音的讲解视频。一套能力，两种形态。
| 形态 | 位置 | 给谁用 |
|---|---|---|
| DSH 插件 | 仓库根目录 | DeepSeek Harness：注册 render_video / list_voices / voice_samples |
| 通用 skill | skills/video-remix/ |
任何 agent：analyze / render / samples / voices 四个 CLI 命令 |
插件本身不含生成逻辑，它只是把 skill 暴露成工具 —— 一套实现，两处受益，修 bug 和加音色都只做一遍。
两种画面
| 模式 | 速度 | 适用 |
|---|---|---|
| cards（默认） | 10 段约 1 分钟 | 教程、说明、命令演示 —— 文字一字不差 |
| ai | 每段几分钟 | 宣传片、创意短片 —— 真实画面，但慢且要 AGNES_API_KEY |
教程类建议 cards，因为 AI 生成会把命令和步骤画糊。
DSH 插件用法
render_video(
title="90秒讲清楚这个插件",
voice={ engine: "edge", name: "zh-CN-YunxiNeural" },
segments=[
{ title: "视频之眼", sub: "让纯文本 AI 看懂视频", narration: "这个插件能让纯文本的 AI 看懂视频。" },
...
]
)
list_voices() // 看看有哪些声音
voice_samples() // 为每个音色生成一段同样的话，供人试听挑选
skill 用法
cd skills/video-remix && npm install # 首次需要装 Edge TTS 依赖
node scripts/remix.mjs voices # 列音色
node scripts/remix.mjs samples --out 音色试听 # 生成全部音色试听包
node scripts/remix.mjs analyze 参考视频.mp4 --interval 2 # 抽帧 + 转写
node scripts/remix.mjs render script.json # 渲染
analyze 产出可读材料（带时间码的拼图 + 逐句台词），文案由模型写，落在 script.json 里 —— 每次生成都可检查、可微调。
音色
在线（14 个中文，神经语音） —— 需要联网：
| 音色 | 说明 |
|---|---|
zh-CN-YunxiNeural |
★ 云希，男声，自然百搭（默认） |
zh-CN-XiaoyiNeural |
★ 晓伊，女声，偏年轻 |
zh-CN-YunxiaNeural |
★ 云夏，男声，少年感 |
zh-HK-WanLungNeural |
★ 雲龍，粤语男声 |
| 其余 | 晓晓、云扬、云健、东北小北、陕西小妮、粤语/台湾各音色 |
本地离线（3 个，Windows） —— 慧慧（女）、瑶瑶（女）、康康（男）。老式合成，机械感明显，但不联网。
跑 voice_samples 会把 17 个音色都用同一段话念一遍，听感比名字可靠。
依赖
| 依赖 | 说明 |
|---|---|
| Node ≥ 18 | |
| ffmpeg | 探测顺序：FFMPEG_PATH → 本 skill bin/ → 从 skill 与 cwd 向上找 _tools/... → PATH |
@andresaya/edge-tts |
在线音色。skills/video-remix 下执行 npm install 安装（不进 git） |
| Windows | 仅离线音色需要；其他平台用在线音色 |
AGNES_API_KEY |
仅 visual="ai" 需要 |
与 dsh-video-eyes 的关系
| dsh-video-eyes | dsh-video-remix | |
|---|---|---|
| 干什么 | 看懂视频（抽帧、时间码、转写、识图） | 做视频（配音、卡片、合成） |
| 工具名 | read_video / read_video_transcript |
render_video / list_voices / voice_samples |
| 冲突 | 无 | 无 |
两者互补，可以串联：read_video 分析参考片 → 模型写稿 → render_video 产出新片。
都不占用 vision_ 前缀 —— dsh-vision-router 会接管该前缀下的所有工具并在视觉模式关闭时隐藏它们，所以两个插件都刻意避开。
Links
More in this category
DayuanJiang/next-ai-draw-io#dsh-plugin★ 36548
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★ 36201
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★ 6962
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★ 5011
Provides bash, PowerShell 7, and high-performance Rust tools for DSH on Windows to reduce token usage.
sixtysevenlf/dsh-blender-plugin★ 1536
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★ 1153
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.