Google adds voice prompting to Docs, Keep, and Gmail via Gemini AI

Google announced voice-based prompting features for Docs, Keep, and Gmail at its I/O 2026 developer conference on Monday, enabling users to create documents, organize notes, and search email through spoken commands instead of typing.

Docs Live enables voice-driven document creation

The headline feature, Docs Live, allows users to create and edit documents entirely by speaking. In a demonstration, Google showed a user verbally instructing the tool to pull résumé details from Drive, incorporate event logistics from an email thread, and add anecdotes in a single unscripted stream of speech.

According to Google, voice enables longer and more complex prompts than most users would type, while current models can follow along even when speakers change direction mid-sentence.

CEO Sundar Pichai claimed users will soon create and edit documents using voice as a matter of course. The company recently launched Rambler, a standalone dictation product built into its Gboard keyboard that removes filler words and handles multilingual code-switching. Rambler shipped earlier this month for Samsung Galaxy and Google Pixel devices.

Keep adds voice-to-structured-notes

Keep is gaining voice capabilities that allow users to dump unstructured thoughts—from gift ideas to grocery lists to home renovation plans—which the AI then sorts into separate, organized notes.

Similar functionality exists in apps like Voicenotes and AudioPen, and desktop dictation tools like Wispr Flow, Monologue, and Aqua Voice. Google's advantage is scale: Keep integrates with the broader Workspace ecosystem, allowing voice notes to flow directly into Docs, Sheets, and other Workspace tools.

Gmail Live provides conversational inbox search

Gmail is gaining Gmail Live, a conversational voice interface for email. Users can ask Gmail to surface specific details—flight confirmation codes, Airbnb check-in instructions, or school schedules—and receive spoken answers drawn from messages. The system handles multi-step requests and understands context.

Broader AI voice integration trend

Google's Cloud Next conference last month showcased agentic AI features across Workspace. Competitors including OpenAI and Apple are embedding voice-first AI into their productivity tools.

The new voice features will roll out this summer for Google AI Premium subscribers and Google Workspace business users. Pricing for the features has not been disclosed separately from existing subscription tiers.

What this means

Google is positioning voice as the primary interface for complex, multi-step AI interactions in productivity software, leveraging Gemini's capabilities to handle unstructured spoken input. The integration across Workspace gives Google distribution advantages over standalone voice note apps, though adoption will depend on whether users prefer speaking to their documents over typing—a behavioral shift that remains unproven at scale. The move signals that major tech companies view voice as critical to the next generation of AI-powered productivity tools.