Notebooklm Studio

NotebookLM Studio

Import sources into NotebookLM, generate user-selected artifacts via CLI, download results locally.

Inputs

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, report, quiz, flashcards, mind-map, slide-deck, infographic, data-table
• Language (optional, default: zh_Hant): applied via notebooklm language set
• Artifact options: format, style, length, difficulty, etc.
• Custom instructions (optional): passed as description to generate commands

Workflow

Steps are sequential gates — do NOT skip or combine steps.

0. Auth precheck — Verify the session is valid:

   notebooklm auth check --test --json
   

1. Parse input & configure artifacts —

   • 1a. Select artifacts
   • 1b. Discuss options (ASK / OFFER / SILENT priority levels)

2. Derive slug — Generate a short kebab-case slug for the notebook name and output directory.

3. Create notebook —

   notebooklm create "<slug> <YYYYMMDD>"
   notebooklm use <notebook_id>
   mkdir -p ./output/<slug>
   

4. Set language — notebooklm language set <confirmed_language>

5. Add sources — For each source: notebooklm source add "<url_or_filepath>"

6. Generate artifacts — Two-tier strategy:

   • Tier 1 (Immediate): mind-map, report, quiz, flashcards, data-table, infographic — use --wait
   • Tier 2 (Deferred): slide-deck, video, audio — use --json, capture task_id for polling

7. Download Tier 1 — Each artifact into ./output/<slug>/

8. Report + Deliver Tier 1 — Present completed artifacts to user

9. Poll + Deliver Tier 2 — Wait for deferred artifacts, download and deliver as each completes

Artifact Types

Requirements

• notebooklm CLI (notebooklm-py)
• ffmpeg (for audio compression)
• playwright (for browser automation)

Error Handling

• Auth errors: Caught by step 0 precheck. Re-login if expired.
• Tier 1 failure: Retry up to 2 times, then include failure note in delivery.
• Tier 2 failure: Notify user per-artifact. Tier 1 already delivered.
• Timeout recovery: Never re-generate on timeout. Re-check status, re-wait if still processing.

Delivery Template

1. Selection rationale (≤3 bullets)
2. Artifact list with paths/status
3. Key takeaways (3-5 bullets)
4. Failures + fallback note (if any)
5. One discussion question