prompt
FreeMultimodal research agent for Google NotebookLM
FreeFree tier
Inputs: url, audio, video, imageOutputs: video
About prompt
A multimodal research and learning agent prompt that orchestrates Google NotebookLM to ingest documents, media, and web sources, then synthesizes them into structured knowledge artifacts such as podcasts, videos, slide decks, reports, quizzes, flashcards, mind maps, and data tables. The prompt is part of the ai-boost/awesome-prompts open-source collection and is based on the notebooklm-py unofficial Python API. It enables citation-grounded answers, deep web research with automated import, and bulk export of various formats.
Key Features
Ingest and index sources from URLs, PDFs, YouTube, audio, video, images, Google Docs, Word docs, EPUBs, Markdown, and plain text
Chat with evidence using citation numbers mapped to source passages
Generate multimodal artifacts: podcasts (audio), videos, slide decks (PDF/PPTX), reports, mind maps (JSON), data tables (CSV), quizzes (JSON/Markdown/HTML), flashcards, and infographics (PNG)
Deep web research with automated import into NotebookLM
Batch downloads and export of quiz, flashcard, mind-map, and slide-deck formats
Pros & Cons
Pros
- Supports a wide variety of input sources (URLs, PDFs, YouTube, audio, video, images, Google Docs, etc.)
- Generates multiple output formats including audio, video, slide decks, reports, mind maps, data tables, quizzes, flashcards, and infographics
- Citation-grounded answers with source references for verifiability
- Free and open-source prompt available on GitHub
- Capable of deep web research with automated source import
Cons
- Requires Google NotebookLM and access to the unofficial notebooklm-py API (not standalone)
- Prompt may need customization for specific use cases or workflows
- Relies on an unofficial Python library which may change or break
Best For
Academic research synthesis from multiple document typesCreating study guides, flashcards, and quizzes from lecture materialsGenerating podcast summaries or debates from research papersBuilding slide decks (PPTX/PDF) from web research or documentsProducing infographics and mind maps for knowledge visualization
FAQ
What input sources does the orchestrator support?
It supports URLs, PDFs, YouTube links, audio files, video files, images, Google Docs, Word docs, EPUBs, Markdown files, and plain text.
What types of outputs can be generated?
The orchestrator can generate podcasts (audio), videos, slide decks (PDF or PPTX), reports, mind maps (JSON), data tables (CSV), quizzes (JSON, Markdown, or HTML), flashcards, and infographics (PNG).
Is this an official Google product?
No, it is an unofficial Python API and agentic skill for Google NotebookLM, originally from the repository teng-lin/notebooklm-py.