Photos & voice
Snap a photo or talk out loud instead of typing.
Many AI apps are now multimodal: they understand photos and your voice, not just typed text. Snap a picture of your fridge, a confusing instruction sheet or a handwritten list, or just talk while you push the stroller, and the AI works with it.
How it works
- 01You add a photo or tap the microphone instead of typing.
- 02The AI turns the image or your speech into something it can understand.
- 03It answers in text, and in many apps, out loud too.
Showing a friend on a video call
Sometimes it's quicker to hold the phone up and say "look at this" than to describe it. That's what photos and voice do with AI. One-handed with a baby on your hip, you can talk through your to-do list, or show it the flat-pack instructions instead of typing them out.
Where you'll use it
Fridge-photo dinners
Snap the fridge, get dinner ideas using what's actually there.
Voice-note brain dumps
Talk through ideas on a walk, then ask for a plan or a post.
Signs and labels
Photograph a German sign, label or instruction sheet and get it explained in English.
Your nap-time experiment
Try both. First, take a photo of your fridge or pantry and send it with the first message. Then tap the microphone and talk through tomorrow.
Photo prompt: Here's a photo of my fridge. Suggest 3 dinners I can make tonight in under 30 minutes using mostly what you can see. Tell me anything I'd need to buy. Voice prompt (say it out loud): "Here's everything on my mind for tomorrow…" Talk for a minute, then finish with: "Turn that into a short, realistic plan for my day."