AI-Powered Language Learning

POINT, TAP,
AND LEARN.

Turn your iPhone camera into a multilingual vocabulary teacher. Detect objects in real time, identify anything with AI, and build your vocabulary from the world around you.

24 FPS
Laptop - ラップトップ
Cup - カップ
Book - 本
ENJA
24
FPS Real-time
11
Languages
3
AI Modes
80+
Object Classes

Your Camera is Your Teacher

Three powerful ways to discover and learn vocabulary from the world around you.

Real-Time Detection

Your camera detects and labels objects at up to 24 FPS. Bounding boxes appear instantly around everything it recognizes — labels translated in real time.

No internet required

Tap to Identify

Tap any object for AI-powered precision. The app captures and analyzes the image, returning context-aware identification with translation and confidence score.

Context-aware AI

Draw to Identify

Draw a custom bounding box around any region. Perfect for isolating a specific item on a crowded table or a particular plant in a garden.

Precision selection

Vocabulary Builder

Every object you identify gets saved to your personal vocabulary. Track encounter counts, confidence scores, and watch your dictionary grow as you explore the world. Words sync to the cloud across all your devices.

Three AI Engines

Choose the right mode for your needs. Fast and free, cloud-powered precision, or fully private on-device intelligence.

Free

YOLO Mode

On-Device, Real-Time

YOLOv26n model runs directly on your device at 15-24 FPS, detecting up to 20 objects simultaneously from 80 trained classes. Zero network calls.

  • ~20-40ms per frame
  • Works fully offline
  • 80 object classes
Precision

Claude AI Mode

Cloud-Powered Precision

Anthropic's Claude Haiku 4.5 vision model identifies brands, species, dishes, architectural styles — anything a world-class AI can recognize.

  • 1-3 second identification
  • ~1 credit per identification
  • 10 free credits on signup
Free

Apple AI Mode

On-Device Intelligence

Apple Vision + Foundation Models pipeline runs entirely on-device. No data leaves your phone. No internet required. No credits consumed.

  • 1-2 second inference
  • Complete privacy
  • Requires iOS 26+

How It Works

Start learning vocabulary in under 10 seconds.

1

Point Your Camera

Open the camera and let YOLO detect objects around you in real time. Labels appear instantly in your target language.

2

Tap to Identify

See something interesting? Tap or draw a box around it. AI identifies exactly what it is and translates it for you.

3

Build Your Vocabulary

Every word is saved automatically. Track your progress, see confidence scores, and watch your dictionary grow from the real world.

11 Languages

Choose any combination of source and target language. Swap them with a single tap.

English
EN
Español
ES
日本語
JA
Français
FR
Deutsch
DE
한국어
KO
中文
ZH
Português
PT
Norsk
NO
हिन्दी
HI
Русский
RU
More...
Coming

Built for Performance

Real-time ML inference, GPU-accelerated rendering, and native performance — no compromises.

60
FPS Rendering
GPU-accelerated Skia canvas
3.25MB
Model Size
YOLOv26n INT8 quantized
20ms
Inference Latency
Per frame on-device
20
Simultaneous Objects
Detected per frame
React NativeExpo SDK 54TensorFlow LiteSkiaSupabaseClaude APIApple Intelligence

Start Learning Today

Point your camera at anything. YOLO mode is free, forever. Sign up and get 10 free credits for Claude AI.

iOS 14+ required. Apple AI mode requires iOS 26+.