Google is rolling out a productivity upgrade to Gemini Live that moves its voice assistant beyond conversation into executing multi-step tasks across a user’s Google apps, the company announced on August 26, 2026. The update, detailed in a post on The Keyword, adds four capabilities: Spark integration for agentic background tasks, a spoken Daily Brief, hands-free Gmail management, and Personal Intelligence, which draws on past chats and connected apps.
Google says 63% of Gemini users already talk to the assistant out loud, and the upgrade is built around that behavior. “Life moves fast, and speaking a prompt out loud is often the quickest way to get help with Gemini,” wrote Neel Joshi, Director of Product Management for Gemini Live.
Spark Runs Multi-Step Jobs in the Background
The most consequential addition is the integration with Spark, Google’s agentic task system. Using natural voice commands, users can set up complex, multi-step tasks that run on their own across Google Docs, Sheets, Drive, and the web. Spark remembers the stated goal as it works and can handle long-running, scheduled jobs across days or weeks, even when the Gemini app is not actively in use.
Google’s examples are deliberately domestic. A user can ramble unstructured thoughts aloud while commuting, and Spark will organize the key themes into a structured outline in Google Docs by the time the user sits down to work. A family can ask Gemini to maintain a weekly meal plan, have it build a high-protein vegetarian menu, and generate a grocery list from recipes saved in Docs.
Spark requires a Google AI Pro subscription or higher, according to the post’s footnotes.
Daily Brief, Inbox Voice Control, and Personal Intelligence
Daily Brief delivers a spoken summary of the day’s to-do list, combining updates from Gmail and Calendar into one digest in response to the prompt “What’s my daily brief?” It is available with a Google AI Plus subscription or higher.
The new inbox feature turns Gemini into a conversational partner for Gmail triage. Users can ask whether any new or urgent emails have arrived (the post’s example is “Are there any urgent emails from the kids’ school today?”) and then search, summarize, star, archive, or delete messages hands-free.
Personal Intelligence, meanwhile, gives Gemini Live memory across past conversations and connected Google apps, including Gmail, Photos, Search, and YouTube. Google frames it as the assistant connecting dots: asking for “the recipe we talked about yesterday” or the name of a restaurant from a past trip pulls the answer from chat history and app data.
The routing between these tools is automatic. In Google’s walkthrough, a user asks “What does my day look like?” while making coffee, gets briefed on the schedule and inbox contents, then follows up with a request to pull event invites from email, create family calendar entries, and add driving times — a job Gemini hands to Spark to run in the background. To use the features, users must opt in by connecting their apps in the Gemini Personal Intelligence settings, then tap the Live icon in the Gemini app.
Where This Fits in Google’s Gemini Push
The announcement extends a run of Gemini deployments across Google’s consumer and enterprise surface in recent weeks. Unite.AI covered Gemini in Chrome opening to all U.S. Android users as Auto Browse went mobile, Waymo bringing the Gemini assistant into its custom Ojai robotaxis, and Google taking Gemini Enterprise into big law with legal-specific agents. The Gemini Live upgrade applies the same agentic pattern to the consumer assistant: rather than answering questions in a single exchange, the system now holds a goal, decomposes it, and works it across apps over time.
For the voice assistant category, the shift is notable in what it asks of the underlying model. Talking through a morning and delegating the follow-on work in one unbroken conversation requires Gemini Live to track intent across turns, decide which tool a request belongs to, and hand off execution without the user specifying the mechanism — a closer approximation of an executive assistant than a search box with a microphone.
The features are rolling out now in the Gemini app, with Spark gated behind the Google AI Pro tier and Daily Brief behind Google AI Plus.
