01What Is Gemini Notebook Voice Mode and How It Works

Gemini notebook voice mode is a new feature that lets you talk to your notebook app on your phone (Android and iPhone) and get spoken answers. You can also record your own voice, and the notebook adds that recording as a source you can ask about later.

In this episode, Julian explains how it works: you speak, the notebook answers out loud, and you can interrupt while it talks. Every answer comes only from the sources you put in that notebook. If the notebook has three client contracts, the voice only knows those three.

It will not drift into other topics.

This makes it different from general AI chat. You get answers that you can check, because the notebook points back to the exact spot in the source where it found the information.

02Key Features in the September Update

The September update brings several new tools. Here are the main ones:

  • Live voice conversations – speak and get spoken answers in about 100 languages.
  • Built-in recorder – record audio that becomes a notebook source, cited like a PDF or link.
  • Interactive learning overviews – a single running document that weaves in summaries, quizzes, flashcards, and mind maps.
  • Quiz upgrades – now with multiple choice, short answer, and fill-in-the-blank questions.
  • Short video overviews – about six seconds long, in more than 80 languages, with narration and simple animations.
  • Interactive reports – generate infographics, mind maps, and custom videos inside a report.

Some features are already rolling out, others are still coming. For example, interactive reports may take a while to generate, and you can set notifications to come back later.

03How to Set Up Gemini Notebook Voice Mode

To get started with Gemini notebook voice mode, follow these steps:

  1. Open the Gemini notebook mobile app on your Android or iPhone.
  2. Make sure you are logged in with a Google account that has access to the feature (AI Ultra subscribers first, then AI Pro and other tiers).
  3. Create or open a notebook that contains the sources you want to talk about (like contracts, PDFs, or meeting notes).
  4. Tap the voice icon to start a live conversation – the app will listen and speak back to you.
  5. Use the recorder icon to capture a spoken idea, meeting, or client call; the app saves the audio as a source in your notebook.
  6. After recording, ask questions about that audio, and the notebook will cite the exact spot where it heard the answer.

If you do not see the interactive report option yet, wait a few weeks because Google is rolling it out to all users gradually.

04How to Use It – Examples from the Episode

Julian shows a simple framework called the “spoken research machine.” It has three moves: record it, ask it, and hand it over.

Record it: Use the new recorder to capture anything useful said out loud. For example, you can record a client call, an idea you have on a walk, or a meeting. The recording drops into your notebook as a source.

Ask it: Use voice mode to ask questions out loud. For instance, you have a long service agreement in your notebook. While at the gym, you ask, “What are the cancellation terms?” The notebook tells you, and you can follow up without opening the app.

Hand it over: Use the output side to turn the information into something you can send to someone else, like a report or a video.

Julian also demonstrates creating an interactive learning report about “OpenClaw.” He selects a template, generates a report, and then scrolls to add infographics, mind maps, and videos. The report builds itself as you read, with recommendations like “add this in, change that.”

05Results and Comparisons Shown

In the episode, Julian compares the old notebook version to the new one. Before, you got a summary and separate buttons for quizzes, flashcards, and mind maps. Now, the interactive learning overview stitches them together into one running document.

He also tests the interactive report generator. It takes a while to generate, based on 10 sources. You can choose between formats like “interactive” and “document.” The document format gives more options, like learning review templates and notifications.

Julian says the tool is “completely different from what I could see a couple of years ago” and calls it “really developed as super powerful.” He notes that it would have been super helpful for studying at university, helping embed information in your brain in a new way.

For SEO, he suggests embedding infographics inside content and using the step-by-step sections for blog posts, social media, and marketing content.

06Tips, Limits, and Mistakes to Avoid

Julian shares several practical tips and warnings.

  • Keep your notebook focused – the voice only knows what is in the sources you add. If you want answers about contracts, do not mix in unrelated topics.
  • Be patient with generation – interactive reports can take time. Use the notification option to come back later instead of refreshing.
  • Edit generated elements – when creating infographics or mind maps, edit them before generating. Julian recommends having more thought about them.
  • Check if the feature is live – some updates roll out over weeks. If you can’t see an option, it may not be on your device yet.
  • Use the quiz feedback – after finishing a quiz, chat with the notebook to learn where you are weak and what to review. You can also edit or add your own questions.

Avoid the mistake of thinking the voice will answer outside your sources. It will not. Also, if you share videos, remember they are short (six seconds) and in a limited set of languages (80+).

07Who Should Use Gemini Notebook Voice Mode

Gemini notebook voice mode is for anyone who works with documents and wants to interact with them hands-free. It is especially useful for business owners, students, and professionals who deal with contracts, meeting notes, client calls, or learning materials.

For business, you can record sales calls straight from the app and ask later, “What objection keeps coming up?” The notebook answers from your calls, with the spot where you heard it. That helps you refine your messaging.

For students, the interactive learning overviews and voice practice are powerful. You can study a topic, ask questions out loud, and get cited answers.

For content creators, the interactive reports allow you to embed infographics and videos in blog posts or social media. This is “really, really powerful for SEO,” says Julian.

Julian also mentions a 30-day roadmap for business use, with one notebook for sales calls, one for proposals and service pages, and one for customer feedback. He offers training inside the AI Profit Boardroom, with coaching calls and a prompts library.

08What's Coming Next

Interactive reports are not fully rolled out yet. Julian shows that you can see the option to try it now and select between two formats: interactive and interactive report. More features will land in the coming weeks.

Google is rolling out interactive learning overviews to all users gradually. If you can’t see it yet, that is probably why.

The voice mode went to AI Ultra subscribers first in the week of September 15, with AI Pro and other tiers following. The recorder started rolling out the week after.

Short video overviews are now available in more than 80 languages, and they are useful for sharing with other people. You can customize them by selecting between cinematic or short explainer styles, switching sources, or changing the language.

Keep checking your app for these updates. The tool is changing fast, and what you can do today may grow next month.