Gemini macOS App Launches Global Voice Interaction
Google officially announced that the Gemini macOS desktop app now supports global voice interaction, enabling users to execute various AI tasks directly within local apps via voice commands, significantly boosting desktop productivity.
已确认
- 操作方式: Users can press and hold the Fn key to activate the voice feature for speech-to-text input.
- 上下文推理: The app intelligently distinguishes between standard dictation and reasoning tasks that incorporate on-screen context. To enable screen context reasoning, users must manually turn on the "Speak to Window" option in the app's settings.
- 支持任务: The feature supports extracting and summarizing information, drafting and rewriting text, and generating and editing images. Additionally, Gemini can transform highlighted text, analyze local files, and generate visual charts directly at the cursor's location.
- 可用范围: The feature is now available globally, primarily supporting English interactions.
为什么重要
- This feature breaks the limitations of a single application window, enabling cross-app global voice control and deeply integrating Gemini's multimodal understanding and reasoning capabilities into users' daily desktop workflows.
2026-07-30 ~ 2026-07-31 · 5 related posts
Primary sources
- Gemini macOS App Gets "Speak to Window": Long-Press Fn for Voice UI — testingcatalog · 2026-07-30
- [source] Gemini macOS App Gets Voice Commands for Global Dictation and Editing — GeminiApp · 2026-07-31
- [source] Gemini macOS App Update: Long-Press FN to Activate Screen Context Reasoning — GeminiApp · 2026-07-31
- Gemini App Launches on macOS with Natural Voice Interaction — emmanuelvivier · 2026-07-31
1 near-duplicate retellings: GeminiApp