Convert spoken words into text
A private and powerful AI that runs locally in your browser
Generate HTML templates using Jinja
Classify images in real-time using labels
Estimate depth from webcam video in real-time
Separate speakers in audio recordings
ML-powered speech synthesis directly in your browser
Segment objects in images by clicking points
Generate text using a sample React app
In-browser speech recognition w/ word-level timestamps
Generate images from text prompts
Transcribe audio to text
Experiment with and compare different tokenizers
Run Gemini Nano locally in your browser with Transformers.js
Classify images in real-time using your webcam
Generate depth map from an image
Generate images using text prompts
Upload an image to detect objects