Skip to content

Google releases Gemini 3.5 Transcribe for macOS app

Gemini

The speech-to-text model provides real-time transcription alongside screen context to summarize local files, conduct research, and generate images.

Key points

  • Supports voice input with screen context to summarize local files and plan research
  • Enables image creation using natural language voice prompts

Why it matters

macOS Gemini users can now use real-time speech and active screen context to process local documents and desktop tasks.

Sources