# Gemini Notebook (NotebookLM) Size Limits: Document, Audio, and Source Constraints

Gemini Notebook (formerly NotebookLM) enforces a 200MB file size limit and 500,000-word ceiling per source, capping standard notebooks at 50 sources. Managing large document collections or multi-hour audio files requires understanding these NotebookLM size limit boundaries and using external indexed storage when research projects expand.

Source: https://fast.io/resources/notebooklm-size-limit/
Author: [Derek Labian](https://fast.io/authors/derek-labian/)
Last reviewed: 2026-10-16

## What Are the Document and File Size Limits in Gemini Notebook?

Google's Gemini Notebook, formerly known as NotebookLM, restricts individual sources to `200MB` or `500,000 words`, with each notebook holding up to `50 sources` on the standard tier, according to Google's official documentation. While Google renamed the service to Gemini Notebook in July 2026, the core ingestion architecture and file boundaries remain identical. When researchers or automated pipelines attempt to feed dense books, multi-hour audio recordings, or comprehensive project archives into a single notebook, import fails silently or returns unhandled upload errors.

Every upload encounters a dual-ceiling architecture. Google evaluates files along two separate dimensions: raw storage volume in megabytes and linguistic density in words. Reaching either boundary triggers an immediate import rejection. A plain text file containing `450,000 words` may occupy less than `3MB` on disk, yet it sits right against the word cap. In contrast, an uncompressed archival scan with high-resolution graphics may reach `195MB` while containing only `8,000 words` of text. Both files are valid inputs, but exceeding either threshold aborts the ingestion process.

The specifications table below summarizes the exact limits across all supported source formats verified against [Google Support documentation](https://support.google.com/gemininotebook/answer/16215270) in October 2026:

| Source Format | File Extensions | File Size Limit | Word / Token Limit | Processing Mechanics |
|---|---|---|---|---|
| Portable Document Format | `.pdf` | 200MB | 500,000 words | Requires extractable text layer; copy-protected PDFs fail |
| Word Processing | `.docx` | 200MB | 500,000 words | Extracts textual copy and tables; macros are ignored |
| Plain Text & Markdown | `.txt`, `.md` | 200MB | 500,000 words | Raw characters ingested directly into the grounding store |
| Spreadsheets & Tables | `.csv` | 200MB | 500,000 words | Tabular structures converted to plain text representations |
| Presentations | `.pptx` | 200MB | 500,000 words | Slide text extracted; embedded speaker notes included |
| Electronic Publications | `.epub` | 200MB | 500,000 words | Flowing book text parsed; embedded media stripped |
| Google Docs | Drive import | Linked file | 500,000 words | Multi-tab documents import as a single source; auto-syncs |
| Google Sheets | Drive import | Linked file | 100k tokens | All workbook tabs combined into one source; 100k token cap |
| Google Slides | Drive import | Linked file | 100 slides | Maximum 100 slides per linked presentation source |
| Audio Recordings | `.mp3`, `.wav`, `.m4a` | 200MB | 500,000 words transcript | Transcribed on ingest; silent or low-quality audio fails |
| YouTube Videos | Public URL | Web stream | 500,000 words transcript | Requires video captions; recent uploads may lack transcripts |
| Web Pages | HTTP / HTTPS | Web scrape | 500,000 words | Main text extracted; paywalls, logins, and images excluded |
| Manual Notes | Direct input | In-app editor | 500,000 words | Text notes created directly within the notebook workspace |

### How Google Measures Word Count Across File Types

Word count enforcement differs from standard LLM tokenization. Underlying Gemini models operate on token vectors, but Gemini Notebook calculates an explicit word count during text extraction. For Western languages, the extraction engine counts whitespace-delimited character sequences. Hyphenated compound words generally register as single units, whereas numerical tables and raw code snippets can inflate counts rapidly because punctuation and separators split numbers into distinct tokens.

Google Sheets represents a notable exception to the standard word count metric. Instead of applying the `500,000-word` ceiling, Google enforces an explicit ceiling of `100k tokens` on spreadsheet imports. Because tabular rows contain repetitive structural markers, cell coordinates, and sparse values, a spreadsheet with thousands of rows can exhaust the `100k tokens` boundary long before reaching the word cap. The platform also aggregates every sheet tab in a Google Sheets workbook into a single source object, making dense multi-tab workbooks particularly susceptible to import truncation.

## How Audio File Sizes and Word Count Limits Interact

Audio file handling introduces a distinct mechanical dynamic that trips up many research teams. Competitors frequently overlook how raw audio file sizes and transcription word counts interact, leaving users confused when audio uploads fail unexpectedly. Google allows direct uploads of audio files up to `200MB`. Supported audio extensions include MP3, WAV, M4A, AAC, OGG, FLAC, OPUS, WMA, AMR, and 3GP. Once uploaded, Gemini Notebook does not store or process the raw audio during user conversations. Instead, an automated Gemini speech-to-text pipeline transcribes the audio into a written transcript at the moment of ingestion. That generated transcript becomes the text source saved into the notebook. This two-stage pipeline creates an asymmetry between file size and duration. The primary limitation on audio uploads is almost always the `200MB` file size ceiling rather than the `500,000-word` transcript ceiling.

Uncompressed high-fidelity audio formats consume substantial storage per minute of recording and reach the file size ceiling quickly, yielding only a fraction of the allowable transcript length. In contrast, voice-optimized compressed audio formats require less storage per hour of speech, allowing multi-hour meeting recordings or interviews to fit comfortably within the upload threshold. Because conversational speech proceeds at an ordinary cadence, the resulting transcript easily stays within the textual capacity of the notebook. The active bottleneck is therefore file compression and format selection, not the textual capacity of the notebook.

### Transcription Quality and Audio Import Failures

The speech-to-text transcription engine requires clear acoustic signal properties to complete ingestion. Google documentation explicitly notes that audio imports fail when a file contains no discernible speech, such as ambient background noise, field recordings, or instrumental tracks. Audio with severe distortion, low signal-to-noise ratios, or heavy overlapping cross-talk can also cause the transcription worker to timeout or discard large spoken passages without user feedback.

A second operational restriction involves Google Drive integration. While Google Docs, Sheets, and Slides can be imported directly from Google Drive using the native picker, Gemini Notebook does not support direct audio imports from Google Drive. Audio files stored in Drive appear greyed out or unselectable in the interface. To import a meeting recording or interview stored in Drive, users must first download the audio file to local storage and then upload it through the local file dialog.

## How NotebookLM Size Limits Vary Across Free and Upgraded Plans

Gemini Notebook organizes research material within individual notebooks, each containing an isolated set of grounded sources. On the standard tier, Google caps each notebook at `50 sources`. This boundary represents the most common operational ceiling encountered by researchers, analysts, and project teams.

Google provides paid plan upgrades that expand notebook quotas and total source capacity. The breakdown below details the published source caps across consumer and workspace tiers verified against Google's [plan availability guide](https://support.google.com/gemininotebook/answer/16213268) in October 2026:

| Plan Tier | Sources Per Notebook | Total Notebooks | Word Cap | File Size Cap |
|---|---|---|---|---|
| Gemini Notebook Standard (Free) | 50 sources | 100 notebooks | 500,000 words | 200MB |
| Google AI Plus | 100 sources | 200 notebooks | 500,000 words | 200MB |
| Google AI Pro | 300 sources | 500 notebooks | 500,000 words | 200MB |
| Google AI Ultra (20 TB Plan) | 500 sources | 500 notebooks | 500,000 words | 200MB |
| Google AI Ultra (30 TB Plan) | 600 sources | 500 notebooks | 500,000 words | 200MB |

Upgrading to an advanced plan increases the number of sources permitted per notebook, moving the limit from `50` up to `600`. However, an upgrade does not increase the per-source file size or word count ceiling. A subscriber on the highest Ultra tier remains bound by the exact same `200MB` file size limit and `500,000-word` cap per source as a user on the standard tier.

Collaboration rules enforce another important constraint: sharing a notebook does not change the source limit for any collaborator. If a project lead on a Pro account creates a notebook containing hundreds of sources and shares edit access with colleagues on standard accounts, those collaborators can interact with and query all sources within that shared notebook. However, the collaborators cannot add sources beyond the notebook owner's plan quota, nor does participating in a large shared notebook expand the `50-source` limit on their personal notebooks.

### The Practical Impact of Source Fragmentation

The `50-source` limit on standard accounts creates friction for projects that aggregate hundreds of research papers, legal filings, customer interviews, or code documentation files. When users exceed the source cap, they must fragment their research across multiple notebooks.

This containerization creates persistent analytical blind spots. The retrieval and synthesis engine operates exclusively within the boundary of a single active notebook. It cannot query across separate notebooks or synthesize findings from disjoint source sets. If market research is split between a Competitor Analysis notebook and a Customer Feedback notebook, the model cannot correlate customer complaints with competitor product features in a single prompt. Researchers must manually copy notes between notebooks or synthesize answers externally, defeating the purpose of an automated research assistant.

## Why Ingestion Fails and Steps to Fix Import Errors

When an import fails in Gemini Notebook, the application displays a generic error message rather than specifying the exact constraint violated. Understanding the root causes of ingestion failures allows teams to resolve issues quickly.

Google documentation identifies three primary causes of direct import failure: the file exceeds `200MB`, the file exceeds `500,000 words`, or the file contains copy-protection locks. Beyond those primary triggers, format-specific limitations account for the majority of rejected uploads.

The following checklist identifies common failure triggers and concrete remediation steps:

* **Copy-Protected and Password-Encrypted PDFs:** Many academic journals, legal filings, and financial statements apply Adobe Acrobat digital rights management or security permissions that disable text extraction. Gemini Notebook cannot bypass encrypted PDF containers. To resolve this, decrypt the document using an authorized utility like `qpdf --decrypt input.pdf output.pdf` before uploading.
* **Image-Only Scanned Documents:** If a PDF consists of raw scanned bitmap images without an embedded OCR text layer, Gemini Notebook may upload the file without generating usable citations or reject the file as empty. Process scanned documents through an OCR pre-processing tool before ingestion.
* **Spreadsheets Exceeding Token Limits:** Uploading a large CSV or Google Sheet with dozens of columns and thousands of rows causes silent truncation or immediate rejection once it hits the `100k tokens` ceiling. Isolate the specific columns and summary tables required for your analysis rather than uploading raw production database dumps.
* **YouTube Video Age and Transcript Availability:** YouTube video imports rely entirely on pre-existing video captions. Videos published within the past seventy-two hours frequently lack indexed automated captions, resulting in import errors. Private videos, unlisted videos with disabled captions, and videos exceeding `500,000 words` in their transcript will fail.
* **Presentation Slide Counts:** Google Slides decks containing more than `100 slides` trigger a hard validation error. Split expansive slide decks into two smaller files before importing.
* **Audio Without Spoken Content:** Audio recordings containing music, ambient office noise, or long stretches of silence fail ingestion because the speech recognition model cannot extract semantic anchor text.

### Techniques for File Splitting and Media Compression

When individual source files exceed the `200MB` or `500,000-word` limits, systematic pre-processing restores compatibility:

For oversized PDF documents, extract page ranges along chapter boundaries using command-line PDF utilities like `qpdf`:

```bash
qpdf --empty --pages input_large_report.pdf 1-150 -- chapter1.pdf
```

For audio files that exceed `200MB`, downmix uncompressed WAV or high-bitrate recordings to mono voice audio using `ffmpeg`:

```bash
ffmpeg -i interview_master.wav -vn -ac 1 -b:a 64k interview_compact.mp3
```

Downmixing to mono voice profiles compresses audio recordings to a fraction of uncompressed storage footprints, fitting multi-hour recordings comfortably within the `200MB` upload ceiling without degrading transcription accuracy.

For spreadsheets exceeding token limits, export only the relevant columns and summary tables to separate CSV files rather than uploading entire relational database dumps with multiple sheet tabs.

## Managing Research Archives That Exceed NotebookLM Source Caps

When research projects outgrow the 50-source boundary or require cross-corpus analysis over hundreds of documents, researchers face a difficult structural decision. Dividing a cohesive project into dozens of separate notebooks fragments synthesis, while manually summarizing documents to fit under word caps introduces human error.

Teams typically explore two common workarounds before seeking dedicated workspace infrastructure:

* **Local Folder Archives:** Maintaining directories of markdown and text files on a local drive gives researchers unlimited file storage, but lacks collaborative sharing and automated retrieval. Without an index, users must write custom search scripts or feed individual files into LLM contexts manually.
* **Standard Cloud Storage:** Keeping files in consumer cloud storage like Google Drive or Dropbox avoids local disk constraints. However, standard cloud drives treat documents as passive blobs. They do not index contents for semantic question-answering or provide grounding citations to connected assistants.

The alternative is an intelligent workspace like [Fast.io](/product/workspaces/), which pairs persistent file storage with automatic retrieval-augmented generation. Instead of attaching static files directly to an isolated notebook container, the entire research corpus lives in an organization-owned workspace where documents are indexed upon arrival.

| Architecture Dimension | Gemini Notebook (NotebookLM) | Fast.io Workspace |
|---|---|---|
| Source Count Ceiling | 50 sources on standard, up to 600 on Ultra | Unlimited files and folders per workspace |
| Per-File Upload Ceiling | 200MB maximum upload size | Up to 100 GB per file on Enterprise |
| Text and Token Limits | 500,000 words per file; 100k tokens on Sheets | Full-corpus indexing without document word caps |
| Retrieval Scope | Isolated strictly to single active notebook | Unified hybrid search across all workspace files |
| Assistant Integration | Closed proprietary web interface | Remote MCP server at `https://mcp.fast.io/mcp/tools` |
| Cloud Storage Ingestion | Google Drive Docs, Sheets, and Slides only | Cloud Sync for Google Drive, Dropbox, Box, OneDrive |

The workflow for managing large research archives operates through three core capabilities:

* **Unified Ingestion via Cloud Sync:** Research teams can import documents directly or connect existing folders from Google Drive, Dropbox, Box, and OneDrive via Cloud Sync. Synchronization operates one-way or two-way, on a schedule or on demand, preserving existing file folder hierarchies.
* **Intelligence Mode for Automatic Indexing:** Turning on Intelligence Mode in workspace settings automatically indexes every document, spreadsheet, PDF, and transcript. Fast.io generates a hybrid search index combining full-text keywords, semantic embeddings, and metadata values, eliminating the need to deploy and manage a standalone vector database.
* **Remote MCP Server for AI Assistants:** External AI clients (including Claude Desktop, Claude Cowork, coding agents, and custom assistants) connect to the workspace using Fast.io's remote Model Context Protocol server. Using Streamable HTTP at `https://mcp.fast.io/mcp/tools` (or `https://mcp.fast.io/mcp/code` for developer agents), assistants query the indexed corpus directly. The assistant searches and retrieves relevant grounded excerpts with source citations on demand, leaving vendor upload limits unaffected while providing instant access to massive document libraries.

Collaborative research also benefits from per-file version history and a detailed activity log. When team members or autonomous agents update documents, extract structured fields, or add annotations, every change is tracked and previous iterations remain recoverable.

## Frequently asked questions

### What is the maximum file size for NotebookLM?

The maximum file size for individual uploads to Gemini Notebook (formerly NotebookLM) is 200MB. This limit applies across all directly uploaded file formats, including PDF documents, Word files, presentations, plain text notes, and audio recordings. Upgrading to higher Google AI plan tiers expands total source counts per notebook, but the 200MB file size ceiling per source remains identical on all plans.

### How many sources can you add to a single NotebookLM notebook?

A standard notebook in Gemini Notebook supports up to 50 sources. Paid plan tiers increase source capacity within an individual notebook: Google AI Plus supports up to 100 sources, Google AI Pro supports up to 300 sources, and Google AI Ultra supports up to 500 or 600 sources depending on the chosen storage allocation. Sharing a notebook with collaborators does not increase the source limit for participating users.

### What is the word limit per document in NotebookLM?

Each uploaded document source in Gemini Notebook is capped at 500,000 words. For spreadsheets and presentations, the platform enforces token and slide caps rather than standard word counts. If an individual source exceeds either the 500,000 words limit or the 200MB size ceiling in NotebookLM, the ingestion service rejects the upload.

### Why do audio files fail to import into NotebookLM even when below the file size limit?

Audio imports fail when recordings lack clear, discernible speech, contain prolonged background noise or silence, or suffer from low signal-to-noise ratios that prevent speech recognition models from generating semantic text. Additionally, direct audio selection from Google Drive is unsupported; users must download audio files from Drive to local storage before uploading.

### How can teams search research archives that exceed NotebookLM source limits?

When research collections exceed notebook source caps, teams can store their full document corpus in an external intelligent workspace like Fast.io. Connecting cloud folders from Google Drive, Dropbox, Box, or OneDrive via Cloud Sync and enabling Intelligence Mode indexes the entire archive for hybrid semantic and full-text search. External AI assistants can then query the indexed repository via Fast.io's remote Model Context Protocol server without attaching static files.

## Sources

- [Google Help: Add or discover new sources for your notebook](https://support.google.com/gemininotebook/answer/16215270?hl=en): NotebookLM restricts individual sources to 200MB or 500,000 words, with each notebook holding up to 50 sources on the standard tier.
- [Google Help: Learn about Gemini Notebook’s plans](https://support.google.com/gemininotebook/answer/16213268?hl=en): Sharing a notebook does not change the source limit for any collaborator, and notebooks support from 50 up to 600 sources depending on the plan tier.

## About Fast.io

Fast.io provides shared workspaces where people and AI agents work on the same files, with built-in semantic search and citation-backed chat over what they hold. Agents reach it through a remote MCP server, a REST API at https://api.fast.io/current/, and a command line client published on npm as @vividengine/fastio-cli. MCP setup is at https://mcp.fast.io/docs: Claude and most MCP clients connect to https://mcp.fast.io/mcp/tools, ChatGPT to https://mcp.fast.io/mcp/operations, and coding agents to https://mcp.fast.io/mcp/code.