ReleaseBytes
gemini Gemini Blog ·

Gemini for macOS adds voice-based natural language features

ai
feature

The Gemini app for macOS now supports voice commands for creating, editing, and summarizing content directly within any desktop application. This feature offers intelligent dictation and optional AI-powered reasoning for complex tasks like summarizing files or generating images. The new capabilities are rolling out globally in English to all users of the macOS app.

  • →Voice commands for intelligent dictation and AI reasoning
  • →Extract and summarize local files or images via voice
  • →Compose and rewrite text using voice commands
  • →Generate and edit images using voice
  • →Global rollout in English for macOS app
Features (4) ›
  • Voice commands for intelligent dictation and AI reasoning

    The Gemini app for macOS now allows users to activate intelligent dictation or advanced AI reasoning by long-pressing the Fn key. This enables users to speak naturally into any window to transcribe text, automatically removing filler words and correcting mid-sentence. Users can opt into Gemini understanding screen context for complex tasks.

  • Extract and summarize local files or images via voice

    Users can now highlight local files, images, or documents on their macOS desktop and use voice commands to instruct Gemini to extract and summarize information. For instance, a user can ask Gemini to summarize a dog's medical history from vet files into an email.

  • Compose and rewrite text using voice commands

    The new Gemini for macOS feature allows users to highlight text anywhere on their screen and use their voice to rewrite it or adjust the tone. The polished version can then be instantly dropped back into the original location, such as turning notes into an executive summary.

  • Generate and edit images using voice

    Users can now employ voice commands to create visuals or iterate on existing designs directly on their macOS desktop. This includes referencing an on-screen illustration to request quick updates or generating images based on conceptual ideas.

Notes (1) ›
  • Global rollout in English for macOS app

    This new voice capability is rolling out globally in English to all users of the Gemini app for macOS. More languages are expected to be added in the future.

Read the original announcement →

https://blog.google/innovation-and-ai/products/gemini-app/speak-naturally-gemini-app-mac-os/

Related releases