Google wants you to talk to Docs, Keep, and Gmail instead of typing

Google is betting that the future of productivity software starts with your voice, not your keyboard. At its I/O 2026 developer conference on Monday, the company unveiled voice-based prompting features for Docs, Keep, and Gmail, all powered by its Gemini AI models.

The headline feature is Docs Live, which lets users create and edit documents entirely by speaking. In a demo, Google showed a user verbally instructing the tool to pull résumé details from Drive, layer in event logistics from an email thread, and sprinkle in a few humorous anecdotes, all in a single, unscripted stream of speech. The idea is that voice enables longer, more complex prompts than most people would bother typing out, and that current models are now good enough to follow along even when a speaker changes direction mid-sentence.

The 💜 of EU tech

The latest rumblings from the EU tech scene, a story from our wise ol' founder Boris, and some questionable AI art. It's free, every week, in your inbox. Sign up now!

CEO Sundar Pichai framed the shift as inevitable, saying that users will soon create and edit documents using voice as a matter of course. It is a bold claim, but the technical groundwork is arguably already in place. Google recently launched a standalone dictation product called Rambler, built into its Gboard keyboard, which strips filler words and handles multilingual code-switching on the fly. Rambler shipped earlier this month for Samsung Galaxy and Google Pixel devices.

Keep is getting a similar voice overhaul. Users will be able to dump a stream of unstructured thoughts, jumping from gift ideas to grocery lists to home renovation plans, and the AI will sort the transcription into separate, neatly organised notes. The concept is not new. Apps such as Voicenotes and AudioPen have offered voice-to-structured-text workflows for years, and desktop dictation tools like Wispr Flow, Monologue, and Aqua Voice have built loyal followings. What Google brings to the table is scale: Keep is already baked into the broader Workspace ecosystem, meaning voice notes can flow straight into Docs, Sheets, and the rest of the suite.

Gmail, meanwhile, is gaining what Google calls Gmail Live, a conversational voice interface for your inbox. Instead of typing search queries, you can ask Gmail to surface specific details, flight confirmation codes, Airbnb check-in instructions, or your child’s school schedule, and get spoken answers drawn from your messages. It is essentially an AI agent for your email, one that understands context well enough to handle multi-step requests.

The broader trend here is clear. Users are asking increasingly complex, multi-part questions of AI tools, and voice is simply a more natural interface for that kind of interaction than a text box. Google is not the only company to notice. Its own Cloud Next conference last month showcased a wave of agentic AI features across Workspace, and rivals from OpenAI to Apple are racing to embed voice-first AI into their own productivity stacks.

The new voice features will roll out this summer for Google AI Premium subscribers and Google Workspace business users. Whether talking to your documents catches on as a mainstream habit remains to be seen, but Google is clearly convinced that the keyboard’s monopoly on productivity is overdue for a challenge.