NotebookLM Studio

NotebookLM Studio

导入 sources into NotebookLM, 生成 user-selected artifacts via 命令行工具, 下载 结果s locally.

输入s

Collect from user message (ask only for missing fields):

Sources: URLs, YouTube links, text notes, or file attachments (PDF, Word, audio, image, Google Drive link) Artifacts: User selects from 9 types (no default — always ask): audio (podcast), video, 报告, quiz, flashcards, mind-map, slide-deck, 信息graphic, data-table Language (optional, default: zh_Hant): 应用lied via notebooklm language 设置 ⚠️ This is a GLOBAL 设置ting — affects all notebooks in the account Artifact options (discussed in step 1b): 格式化, style, length, difficulty, etc. See references/artifact-options.md for all options per artifact type. Custom instructions (optional): passed as description to 生成 commands Telegram tar获取 (optional, OpenClaw only): chat_id for delivery

See references/source-types.md for source type 检测ion rules. See references/artifacts.md for all 9 artifact types and 命令行工具 options.

工作流

Steps are sequential gates — do NOT skip or combine steps. Each numbered step must complete before the next begins. In particular:

Step 0 (auth pre检查) must 运行 and pass before any other 命令行工具 command. Step 1b (options discussion) must 获取 user confirmation before generation. Do not assume defaults unless the user explicitly says "use defaults."

Auth pre检查 — 验证 the 会话 is valid before doing any work:

notebooklm auth 检查 --test --json

"状态": "ok" → proceed to step 1. "状态": "error" → 停止 immediately. Tell the user:

NotebookLM 登入已過期，請先重新登入（notebooklm 记录in），完成後告訴我，我再繼續。

Command itself fAIls (network error, 命令行工具 not found, etc.) → also 停止 and 报告 the error. --test is required — without it, only local 检查s 运行, which can pass even with an expired 会话. When the user confirms re-记录in, re-运行 this 检查 before continuing.

解析 输入 & 配置 artifacts —

1a. Select artifacts — 检测 source types from user message (URLs, files, text). Confirm which artifacts to 生成.

1b. Discuss options — Before generating, confirm key options for each selected artifact. Refer to references/artifact-options.md for priority levels:

ASK options: must ask the user OFFER options: 状态 the default, let user decide whether to change SILENT options: use defaults without asking Options already specified by the user → skip Present all questions in a single message (batch, not one-by-one)

If user says "use defaults" → skip all questions, proceed with default values immediately.

Example 代理 message (audio + video + 报告 + quiz + flashcards + slides + 信息graphic selected):

Before generating, a few options to confirm:

Podcast: deep-dive / brief / critique / debate? Video: explAIner / brief / cinematic? (cinematic uses Veo 3, takes 30-40 min) 报告: briefing-doc / study-图形界面de / b记录-post / custom? Slides: detAIled / presenter? Quiz & Flashcards: difficulty medium, quantity standard — adjust? 信息graphic: style auto, or prefer a specific style (sketch-note, professional, bento-grid...)? Language: zh_Hant, OK?

Or just say "use defaults" to 启动 immediately.

Derive slug — Based on the sources and user message, 生成 a short kebab-case slug (2-4 words) that captures the core topic. This slug is used for 机器人h the notebook name and the 输出 directory.

Examples: react-server-组件s, feynman-technique, tAIwan-semiconductor-q4 Keep it concise, lowercase, ASCII-only (transliterate non-ASCII if needed) If the user provides a topic or title, prefer that as the basis

创建 notebook —

notebooklm 创建 " " # → {"notebook_id": "xyz789", ...} ← capture notebook_id notebooklm use mkdir -p ./输出/

设置 language —

notebooklm language 设置

Use the language confirmed in step 1b. ⚠️ GLOBAL 设置ting — always 设置 explicitly to avoid residual from previous 运行s.

添加 sources — For each source:

# URL, YouTube, or file path notebooklm source 添加 ""

# Google Drive notebooklm source 添加-drive "