Lesson 7 of 8
Voice & images
6 min read
Typing is just one way in. You can also speak to ChatGPT and hear it answer — and ask it to draw the thing you're describing, right there in the chat.
Talk to it
Voice mode turns ChatGPT into a conversation. You speak, it listens and replies out loud, and you can interrupt or change tack mid-sentence — handy while cooking, walking, or practising a language. It can even use your camera to look at what you're pointing at.
Voice makes ChatGPT hands-free and conversational — closer to talking with someone than typing at a search bar.
It draws, too
Ask for a picture — "a cosy reading nook, watercolour" — and ChatGPT generates it directly, no separate art app. Because it's the same chat, you just keep talking to refine it: "make it evening," "add a cat." It edits the image from your words.
Image generation lives inside the conversation, so you shape a picture the same way you shape text — by describing the change you want.
Generated images can get small details wrong — hands, text on signs, exact logos. Lovely for ideas and illustration; double-check before anything official.
The shape of it
- —Voice mode lets you speak with ChatGPT hands-free, and it can use the camera.
- —It generates images from a description, right in the chat.
- —You refine a picture by describing the change, just like editing text.
You want a birthday-card illustration of a cat astronaut — then the cat in red instead of blue. How?
Continue in the app
Take the whole Get the most out of ChatGPT course — tracked
Get your personalized path, progress and streaks in the app — this lesson and every next one, in order.