Google adds voice prompting to Docs and Keep
▼ Summary
– Google announced voice-based prompting for Workspace apps like Docs, Keep, and Gmail to help create drafts, take notes, and search emails.
– In Docs, voice can fetch résumé details from Drive, add event logistics from an email, and include anecdotes in one go.
– Google is adding a feature to Keep that uses AI to turn voice transcriptions into structured notes or lists.
– In Gmail, users can converse with Gemini via voice to ask for details like flight info or booking codes.
– Google’s voice features understand when users change their mind mid-query, allowing multi-task requests in a single turn.
At the Google I/O developer conference, the company unveiled a voice-based prompting feature for its Workspace apps, including Docs, Keep, and Gmail. This new capability allows users to create drafts, take notes, and search for emails simply by speaking.
In Google Docs, you can now generate a full draft using your voice. During a demo, Google illustrated how a user could pull résumé details from Drive, incorporate event logistics from an email directly into the document, and even add humorous anecdotes , all through spoken commands.
Previously, users had to type everything manually, often resulting in short sentences and multiple follow-ups that turned into a time-consuming, multi-turn conversation. Google’s approach lets you use longer sentences or request several tasks at once. The system also recognizes when you change your mind mid-request, allowing for seamless adjustments within the same conversational turn.
Google CEO Sundar Pichai noted that, in the future, users will be able to both create and edit documents entirely with their voice.
Beyond Docs, Google is adding a similar feature to Keep. Users can verbally dump their thoughts into the app, and AI will transform that transcription into a structured note or list. While this functionality has existed in third-party notetaking apps like Voicenotes and AudioPen for years, and more recently in dictation tools like Wispr Flow, Monologue, and Aqua, Google is now integrating it natively.
Earlier this month, Google released its own dictation product, Rambler, which is built into Gboard and works across various apps.
The company is also bringing voice-based functionality to Gmail. With this update, users can converse with Gemini to ask for specific details, such as their next flight, an Airbnb booking code, or the time of a physician appointment.
As tech companies embed AI into every product and feature, users are becoming accustomed to asking lengthier queries. Voice often proves to be a simpler input method for blurting out long sentences or describing complex, multistep requests. The current generation of AI models is also adept at understanding when users change their minds mid-sentence, adjusting the final output accordingly. Google is closely following this trend and expanding voice capabilities across its app ecosystem.
(Source: TechCrunch)
