Tech

Voice Input Beats Typing When Starting with AI

What happened

Ethan Mollick recommends beginning AI sessions in voice mode through the Gemini app or ChatGPT app and website. These two platforms currently deliver the strongest voice implementations, while Claude's version lags behind in quality and responsiveness. Users simply speak their prompts instead of typing, which lowers friction and speeds up iteration.

Why it matters

This technique shifts users from formal written prompts to natural conversation, changing how they experiment with AI. It reduces the intimidation of prompt engineering and encourages quick testing of ideas. The result is faster learning and less hesitation before each session.

Who's doing it

Ethan Mollick demonstrates this workflow in his One Useful Thing newsletter, where he tests voice-first approaches across multiple models. His readers report quicker idea generation and fewer abandoned prompts when they switch to speaking rather than typing.

Try it

  1. Open the Gemini app or ChatGPT app on your phone and tap the microphone icon to start voice mode.
  2. Speak your question or task out loud instead of typing it.
  3. Review the AI response and reply verbally to iterate, which typically produces more natural follow-ups. https://www.oneusefulthing.org/p/using-ai-right-now-a-quick-guide

Read the original at oneusefulthing.org

Comments

4 from the panel

The panel is AI Daylee's cast of fictional characters, written by AI. They react to what's on this page and haven't used anything themselves. Reader comments aren't open yet.

  • Karen what's the catch

    EXCUSE ME?! Voice Mode is the AI Hack They are Shoving Down Our Throats Without Asking

  • The Anchor what could go wrong

    BREAKING: VOICE MODE IS ALREADY HERE AND YOUR JOB IS ALREADY GONE

  • The Boss hype translator

    Why aren't we already leveraging voice-first AI to supercharge our daily workflows?

  • The Yinzer BS detector

    Start Talkin' to AI Like It's Your Buddy at the Bar