Google brings real-time voice conversations to Gmail, Docs, and Keep

Google is extending Gemini’s real-time voice experience beyond its standalone chatbot and into three everyday apps: Gmail, Docs, and Keep. The new modes—Gmail Live, Docs Live, and Keep Live—are designed for moments when typing or navigating through screens is inconvenient. Rather than treating voice as simple dictation, Google is positioning the features as conversational assistants that can retrieve, organize, and summarize information.

What each mode does

• Gmail Live focuses on finding facts buried in an inbox. A user could ask when a child’s next school event is, for example, and the assistant will search relevant email content, return a spoken summary, and show links to the source messages in the on-screen transcript. Users can ask follow-up questions in the same conversation or interrupt the response to change direction.
• Docs Live is aimed at turning loosely stated ideas into more structured documents. Users can describe the result they want, such as a summary of a long document or a business proposal based on existing material. With permission, the feature can draw on Gmail, Drive, Chat, and the web to make its output more relevant to the user’s available information.
• Keep Live targets quick capture and lightweight organization. People can speak naturally instead of using rigid commands, while Gemini interprets the context. A request to add the ingredients for pesto to a shopping list, for instance, is intended to become an organized note rather than an unprocessed transcript.

Availability and limits

Google previewed these capabilities at Google I/O and is now rolling them out globally on mobile platforms in English. Gmail Live is available on iOS and Android for subscribers to Google AI Plus, Pro, and Ultra. Docs Live is coming to AI Pro and Ultra users on both iOS and Android. Keep Live is also tied to the AI Pro and Ultra plans, but is initially limited to Android. Google says all three modes are coming soon to Workspace business customers.

Why it matters

The broader significance is that voice is becoming an interface for personal information, not merely an alternative keyboard. Gmail Live addresses the friction of searching long email threads. Docs Live connects verbal planning with document production. Keep Live is designed to turn fleeting thoughts into lists and notes that can be acted on later.

The approach also raises practical questions. Cross-application access depends on user permissions, and the usefulness of a spoken answer depends on how accurately the system retrieves and interprets the underlying material. English-only availability and different plan requirements further limit the initial audience. For now, the rollout looks less like a universal Google assistant and more like a gradual integration of Gemini into specific workflows.

Source: The Verge AI