Google’s source-grounded research notebook, renamed Gemini Notebook in 2026, that answers questions and builds audio and video overviews from your files.

Pros
  • Answers stay grounded in the sources you upload
  • Audio and Video Overviews turn dense material into summaries you can listen to or watch
  • Per-notebook cloud computer can run code for data analysis
  • Generous free tier tied to a regular Google account
Cons
  • Rename to Gemini Notebook may confuse users searching for the old name
  • Compute-based limits make heavy use harder to predict
  • Newest features reach Ultra subscribers before free users

Google introduced NotebookLM in 2023, after starting it as Project Tailwind, and on July 16, 2026 renamed it Gemini Notebook while keeping it a standalone product. The old notebooklm.google address now redirects to notebook.google, and existing notebooks carried over unchanged.

The core idea is a notebook that answers questions grounded in the sources a user adds, such as uploaded PDFs and documents, instead of the open web. Studio outputs turn those sources into Audio Overviews, Video Overviews and reports, and Deep Research can gather additional material. Each notebook now also gets a secure cloud computer that writes and runs code for data analysis on the uploaded files, available first to Google AI Ultra subscribers and rolling out to Pro users on the web. Notebooks sync with the Gemini app, and Google says access through AI Mode in Search is coming. Paid Google AI plans raise source and usage limits over the free tier.

Students preparing for exams, researchers working through papers and teams building onboarding material get the most value, because answers stay anchored to their own documents. Since September 2026 usage limits are compute-based, refreshing every few hours with a weekly cap, so heavy users can hit the ceiling on the free tier. It is a research companion rather than a full writing or project management tool.

Top-Rated AI Tools
OpenAI's general-purpose AI assistant for writing, research, coding and everyday questions, with a free tier and paid plans from Go to Pro.
AI audio platform for lifelike text-to-speech, voice cloning, dubbing, transcription, music, and conversational voice agents, available in a web studio and via API.
Anthropic's AI assistant for long-form writing, analysis and coding, with Projects, Artifacts, Research and Claude Code on paid plans.
Agent-centered code editor from Anysphere, now part of SpaceX, with desktop and cloud agents, a CLI, Bugbot code review and multi-model support.
Independent AI image generator known for its distinctive aesthetic, now on the V8.2 model with an Edit Model and image-to-video animation.

NotebookLM (Gemini Notebook)
4.7/5