NotebookLM API (Gemini Notebook API) v1

September 29, 2026 (October 15, 2026)

This is a third-party API for NotebookLM (Gemini Notebook) by Google. The useapi.net NotebookLM API (Gemini Notebook API) is a REST API that turns web pages, PDFs and YouTube videos into podcasts (Audio Overviews), Video Overviews, slide decks and quizzes on your own Google account, free plan included, with no Enterprise license or Google Cloud project. Google renamed NotebookLM to Gemini Notebook. Paid Google AI plans raise the usage limits.

Create notebooks, add web pages, YouTube videos, pasted text, uploaded files, Google Drive files and ebooks from the account’s Google Play Books library as sources, and ask questions that are answered from those sources with citations. Every Studio output is available: Audio Overviews, Video Overviews, reports, interactive reports, tables, quizzes, flashcards, infographics, slide decks and mind maps. Audio, video, slides and infographics come back as downloadable files (m4a, mp4, pdf, pptx, png). Quizzes, flashcards and mind maps come back as JSON. An interactive report suggests its own infographics, slide decks, mind maps, quizzes and flashcards, and each one can be generated on its own. Reports export to Google Docs and tables to Google Sheets, and finished artifacts can be copied to another notebook.

Let Google find sources for you with Discover sources and Deep Research, then import the ones you want, along with the Deep Research report. Notebooks also keep notes, which can be turned into sources or filled from a whole chat conversation, plus mind map notes. Sources can be grouped with labels that Google assigns by topic, searched for the passages that match a query, appended to, and copied to another notebook. Notebooks can be grouped into collections. Chat keeps its history and can be configured with a learning-guide or custom persona and a longer or shorter answer length. A notebook can be copied with its sources, its guide gives Google’s summary with suggested reports and questions, and it can be shared with people or by link.

No code? Import the n8n template that turns web pages, YouTube videos or a blog’s RSS feed into a NotebookLM podcast.

You can also skip the notebook entirely. Send urls or text straight to POST /artifacts and the API creates a notebook for that request on one of your accounts, picked by load and remaining usage.

Why useapi.net instead of a free library

useapi.net is a third-party API and is not affiliated with Google.

Nothing to run on your machine. The API is hosted, so jobs keep running when your laptop is off: no Chromium download, no local server, no tunnel and no browser left open.
Sign in once, we keep you signed in. The guided browser setup connects your Google account once, and we keep the session fresh, with no cookies to copy or refresh. If Google ever signs it out, you get an email with a one-minute re-add link.
A hosted MCP server, 57 tools. Add it to Claude Code, Cursor or VS Code with one line. Nothing to install, and every notebook, source, chat and Studio output is available to your AI assistant.
Plain REST from any language. Call it from Node.js, Python, bash, n8n, Make or a cron job with an API token. A Postman collection and an LLM-friendly spec cover every endpoint.
Jobs tracked for you, with webhooks. Every podcast, video, slide deck and research run is a server-side job. Poll it, or pass replyUrl and get the finished result posted to your endpoint.
Several Google accounts, balanced automatically. Connect 3 accounts per subscription, up to 100; each new job goes to one that is healthy, has a free slot and still has usage left.
Links in, podcast out. Send URLs or text to one endpoint and get an Audio Overview, Video Overview, slide deck or quiz back, with no notebook setup.
Ready-made n8n workflows and an agent skill, on your free or paid Google plan, for a flat $15/month that covers every useapi.net API.

Pricing

A flat $15/month to useapi.net, which covers every useapi.net API, not only Gemini Notebook. Each subscription lets you connect 3 Google accounts, up to 100 in total. Generation runs on your own Google accounts, so there is no per-call or per-audio charge from us, and Google’s own usage is included in whatever plan the account has, including the free one.

	useapi.net Gemini Notebook API	Google’s Gemini Notebook Enterprise API
Accounts	Your own Google accounts, free or paid plans	Enterprise licenses in a Google Cloud project
Price	$15/month flat	Per-user Enterprise licenses
Chat with citations
Deep Research
Audio Overviews
Video Overviews, slides, infographics, reports, quizzes, flashcards, mind maps
Status	Third-party	Preview (Pre-GA)

One Google account, four APIs

The same Google AI plan powers several useapi.net APIs, each from its own allowance, so one Google account connected to all of them gets the most out of the plan:

Google Flow API: Veo 3.1 and Omni 1.1 Flash video, Nano Banana images up to 4K, from Flow credits.
Google Vids API: Omni 1.1 Flash video with avatars and voices, from the Vids allowance, which does not use Flow credits.
NotebookLM API (Gemini Notebook API): chat with sources, Deep Research and every Studio output, from the Gemini Notebook usage limits.
FlowMusic API: full songs with Lyria in Google Flow Music, which signs in with a Google account too, on Flow Music’s own plans.

Each API is set up on its own setup page, and one useapi.net subscription covers all of them.

Start using the API

A single $15/month subscription covers every API on useapi.net — one token, all services. You connect up to 3 of your own provider accounts per service, and useapi.net handles the REST API, load balancing, and polling. Need more accounts? Each extra subscription is $10/month and adds 3 more accounts per service.

Subscribe — $15/month Pay with crypto

Pricing and volume options — full refund within the first 14 days if you have fewer than 50 successful generations. Already subscribed? Change the quantity in the Stripe Customer Portal instead of buying again.

Run NotebookLM at scale

It is built to run unattended. With several accounts connected, each new job goes to an account that is healthy, has a free job slot and still has usage left for that type, so nobody has to watch Google’s 5-hour and weekly budgets or decide which account runs next. Jobs are tracked on our side: poll GET /jobs/jobid or pass replyUrl to get the finished job record posted to your webhook. When every account is busy or out of usage, the call answers 429, and when Google names the reset time it comes back as retryAt, so your code decides how to handle the load: wait until then, send the next batch to another account with email, or lower the rate. No human has to step in.

How much one account can generate

Google has no fixed daily counts for Gemini Notebook. Each Google account gets a usage budget that refills every 5 hours, plus a weekly budget. The table shows how many of each you can start with a full 5-hour budget, counting each job at Google’s own estimate:

Studio action	Free	Pro	Ultra
Audio Overview	2	9	181
Video Overview	2	9	183
Video Overview, short	2	11	229
Video Overview, cinematic	not available	1	25
Report	23	92	1846
Table	16	67	1355
Quiz	43	175	3478
Flashcards	52	212	4285
Infographic	9	37	745
Slide deck	1	7	146
Mind map	66	263	5217
Chat question	62	243	4897

These are minimums. A job usually costs less than Google’s estimate once it finishes, so you get more: a short Audio Overview on Free measured 3 per 5-hour window, not 2. The weekly budget covers about 21 full 5-hour windows, so an account used around the clock runs out before the week ends. To generate more, connect more accounts: the API spreads new notebooks across them.

Plan limits on notebooks and sources:

Plan	Notebooks	Sources per notebook
Free	100	50
Pro	500	300
Ultra	500	600

These numbers are Google’s and can change. GET /accounts/email returns the live usage of each account, the reset time of both windows and every action’s current estimatedCostPercent.

Questions

Does NotebookLM (Gemini Notebook) have an API?

Yes for regular Google accounts, through useapi.net. Google’s only NotebookLM API, the Gemini Notebook Enterprise API, needs Enterprise licenses in a Google Cloud project and covers notebooks, sources, sharing and Audio Overviews (as of October 2026). The useapi.net NotebookLM API (Gemini Notebook API) runs on your own free or paid Google account and adds chat with citations, Deep Research and every Studio output.

How much does the NotebookLM API cost?

A flat $15/month, with no per-call or per-podcast charge: generation runs on your Google account’s own usage, free plan included, while Google’s Enterprise API needs paid Enterprise licenses. The subscription covers 3 Google accounts, up to 100, and every other useapi.net API. It is refunded in full within 14 days if you made fewer than 50 successful generations (refund policy).

Is there a NotebookLM API key?

Google issues no NotebookLM API key for regular accounts, so you call it with a useapi.net API token and connect your Google account once through the automated browser setup: sign in with Google, with no cookies to copy and no Google Cloud project. We keep the session signed in, and if Google ever signs it out, you get an email with a one-minute re-add link.

Can I generate NotebookLM podcasts (Audio Overviews) with the API?

Yes, and Video Overviews too, which Google’s Enterprise API doesn’t offer (as of October 2026). Send links or text to POST /artifacts and download the podcast as .m4a, a Video Overview as .mp4, slides as .pdf and .pptx or an infographic as .png. No code? The n8n tutorial turns web pages, YouTube videos or an RSS feed into a podcast.

Setup Gemini Notebook

MCP Server Use NotebookLM from Claude Code, Cursor, VS Code and other MCP clients
GitHub examples Node.js, Python and bash, a Colab notebook, two n8n workflows and an agent skill for Claude Code and Codex
Google Account Setup scripts for a clean, single-use Google sign-in (Windows, macOS, Linux)
Postman collection (October 15, 2026)
LLM-friendly API spec Feed this to your LLM to build integrations
n8n template: NotebookLM Podcast App Turn links or an RSS feed into a podcast you play in the browser, ready to import