Google adds voice prompting to Docs and Keep

At the Google I/O developer conference, Google announced that it is bringing voice prompting to Workspace apps like Docs, Keep, and Gmail. These features can help you create drafts, take notes, and search for emails.

In Docs, you can create a draft of a document using your voice. For example, in a demo, Google showed that a user can fetch biographical details from Drive, add event logistics from an email at the top of the document, and even include some funny anecdotes.

Previously, users had to type all of this, and it is possible, while typing, to write short sentences and then various follow-ups, resulting in a multi-turn conversation that takes time. Google’s idea is that by using voice, you can use long sentences or ask for multiple tasks at once. Additionally, the feature understands when you change your mind and ask to change details in the same conversation.

Google CEO Sundar Pichai said that in the future, users will be able to create and edit documents using their voices.

What’s more, Google is adding a way to use your voice to transcribe your thoughts into Keep, and the app will use artificial intelligence to turn that transcription into an organized note or list. Note-taking apps like Voicenotes and AudioPen added this type of feature a few years ago. Recently, dictation apps like Wispr Flow, Monologue, and Aqua have built this functionality into their voice typing products.

Earlier this month, Google released its own dictation product called Rambler, which is built into Gboard and works across apps.

Along with Docs and Keep, the company is adding voice-based functionality to Gmail. With the new feature, users will be able to talk to Gemini and ask about details like their next trip, an Airbnb booking code, or the time of a doctor’s appointment.

Tech companies are cramming AI into all their products and features, and as a result, users have become accustomed to asking longer queries.

In some cases, voice is an easier input method for pronouncing long sentences and queries that describe complex, multi-step requests. Moreover, the current generation of models is good enough to understand if users change their mind about something mid-sentence and output the final query accordingly. Google is paying attention to this trend and adding more voice features across its apps.

Follow the rest of the important news for Google IO 2026

Google search is over, you know

Google updates Gemini to address ChatGPT and Cloud

Google offers Gemini Spark, a 24/7 proxy assistant with Gmail integration

How to use Google’s new information agents