Converse with AI Without Using Your Hands
While cooking, driving, holding a baby—AI is exactly useful when both hands are full. Here's how to use voice input and read-aloud.
3 Ways of Voice Input
1. AI App's Voice Conversation Mode
The most natural and popular way. Speak and AI replies by voice.
- ChatGPT: tap the voice-conversation icon (headphone shape)
- Gemini: mic button, or "OK Google"
- Claude: voice input in the iOS / Android app
2. OS Standard Voice Input
Voice-to-text with the keyboard's mic button, send to the AI screen.
- iOS: keyboard mic icon
- Android: Gboard mic button
3. Dedicated Apps
- Whisper (OpenAI): high-accuracy speech recognition
- Otter / Notta: meeting recording → transcription
Voice Read-Aloud (Hear AI's Reply)
1. The AI's Own Read-Aloud Feature
- ChatGPT: play with the speaker icon
- Gemini: auto-plays in voice conversation mode
2. OS Read-Aloud
- iOS: Settings → Accessibility → Spoken Content → "Speak Screen" ON
- Android: TalkBack (Accessibility)
Convenient Use Scenes
Kitchen (Cooking)
"I have cabbage, pork, eggs in the fridge. A recipe in 15 min?" → AI proposes 3 by voice "For recipe 2, read the steps in order. Pause after each step"
Driving
"Is the next light a right? right?" (navigation aid) "Today's news key points in 3 minutes" "Reply to email by voice. To Mr. XX, want to push tomorrow's meeting 30 min"
Parenting (Hands Full)
"My 3-year-old has a 38°C fever. Hospital now? watch?" "Baby food, when can eggs be included?" "3 nursery rhymes to sing with a kid"
Walking/Exercise
"Let's practice English conversation. Today's theme is travel" "Beginner leg-training menu at the gym" "Audio reading of a book to hear while walking"
Tips for Voice Conversation
- Speak in segments: too-long questions are easily misrecognized
- Watch proper nouns: "Claude" "Gemini" can be miss-converted
- Watch ambient sound: TV/other conversation mixes in
- Quiet environment recommended: accuracy rises
Tips for Read-Aloud
- Speed adjustment: many find 1.25-1.5x easier to follow
- Voice preference: switch male / female / neutral
- Summarize before reading long text: "read 3 key points by voice"
Sticking Points
- Mic permission: allow on first app launch
- Earphones recommended: when you don't want others to hear
- Background: opening another app interrupts (OS-dependent)
- Data usage: voice conversation uses more than usual, Wi-Fi recommended
Application: Bluetooth Linkage
- Voice conversation from AirPods, SONY headphones
- Usable while driving via car Bluetooth
- Smart-speaker (Alexa, Google Home) linkage also possible
Next Step
The foundations are roughly covered. Next, the practice chapter proceeds to concrete use cases like learning, health, chores, money.
