Google is rolling out a sweeping productivity upgrade to Gemini Live, embedding agentic capabilities that let users set up complex, multi-step tasks with voice commands alone. The update, announced August 26, 2026, integrates Gemini Live with Spark, a new automation engine that works across Google Docs, Sheets, Drive and the web, while also adding hands-free email management, spoken daily briefings and deeper memory features.

The company said 63% of Gemini users already interact with the assistant out loud, and the latest changes are designed to turn those spoken prompts into completed work. “Speaking a prompt out loud is often the quickest way to get help,” Google said in its announcement. “Today we’re rolling out a major productivity upgrade to Gemini Live, bringing in powerful agentic capabilities so you can do more with your voice than ever before.”

Spark is the centerpiece of the update. Users can describe a multi-step goal in natural language, and Spark will execute it in the background, handling long-running or scheduled jobs across days or weeks even when the app is not actively in use. Google offered several examples: a user brainstorming a project can ramble unstructured thoughts into Gemini while on the go, and Spark will organize key themes into a structured outline in Google Docs by the time they sit down to work. A parent can ask Gemini to maintain a weekly meal plan, including a high-protein vegetarian menu and an instant grocery list based on recipes saved in Docs.

Spark requires a Google AI Pro subscription or higher.

The update also brings the Daily Brief into Gemini Live. Users can say, “What’s my daily brief?” and receive a spoken summary of their most important updates from Gmail and Calendar in a single digest. The feature is aimed at answering the question “what should I care about today?” without looking at a screen. Daily Brief is available with a Google AI Plus subscription or higher.

For inbox management, Gemini Live now acts as a conversational partner for email sorting. Users can ask “Any new emails?” or “Are there any urgent emails from the kids’ school today?” and then search, summarize, star, archive or delete messages entirely by voice.

Google is also expanding what it calls Personal Intelligence, a memory layer that lets Gemini connect the dots across past conversations and connected Google apps including Gmail, Photos, Search and YouTube. A user might ask, “What was the name of that restaurant we went to when we visited New York last summer?” or “Can you pull up the recipe we talked about yesterday?” and Gemini will pull the answer from chat history and linked apps.

The assistant is designed to route tasks automatically without requiring users to specify which tool to use. Google described a scenario where a user asks “What does my day look like?” while making coffee. Gemini briefs them on their morning schedule and flags school newsletters and sports schedules in the inbox. The user then follows up: “Can you grab those event invites from my email, create family calendar events for them, and include the driving times?” Gemini hands the job to Spark, which completes it in the background.

To use the new features, users must opt in to app connections in Gemini’s Personal Intelligence settings, then tap the Live icon in the Gemini app and start talking.

The Live upgrade follows Google’s August 25 launch of intelligent dictation in the Gemini app for macOS. That feature lets users long-press the Fn key to speak naturally, with the app transcribing words into clean text at the cursor. Filler words such as “uh” and “um” are removed automatically, mid-sentence corrections are handled seamlessly, and the output is formatted for immediate use. The dictation tool works across any desktop application, and a companion “Speak to Window” feature uses on-screen context to rewrite, summarize or refine content in an email or document without switching to a separate chatbot interface.

The macOS dictation feature is rolling out globally in English, with additional languages planned. The Gemini app requires macOS Sequoia 15.0 or later, at least 8 GB of RAM and roughly 200 MB of installation space. It is free to download.

Google has been steadily expanding Gemini’s voice capabilities since late July 2026. The company’s push into agentic, voice-driven productivity places it in direct competition with Apple’s built-in macOS dictation and Microsoft’s AI Copilot, both of which face pressure as Google continues to integrate generative AI into everyday workflows.

For users, the combined effect of Spark, Daily Brief, hands-free email and Personal Intelligence is an assistant that can move from summarizing a morning schedule to executing multi-day projects without requiring the user to touch a keyboard. Google framed the update as a way to “clear out the mental clutter” and let users get back to their day.

Note: Spark is available with a Google AI Pro subscription or higher. Daily Brief is available with a Google AI Plus subscription or higher. Intelligent dictation for macOS is currently limited to English.