Whisper Web
Transcribe spoken audio into written text
A collection of my favorite WebML demos, built with Transformers.js!
Transcribe spoken audio into written text
In-browser background removal
Experiment with and compare different tokenizers
Generate a depth map from any uploaded photo
A private and powerful AI that runs locally in your browser
Transcribe audio files to text instantly
Segment objects in images using click‑based masks
In-browser text-to-music w/ Transformers.js!
Chat with a private AI model locally
Real-time object detection w/ 🤗 Transformers.js
Convert typed text into spoken audio
In-browser WebGPU background removal
Retrieve relevant texts using a transformer-powered search
Generate AI text instantly in your browser
Play a fun doodling game
Find images by typing a natural language description
Segment objects in images directly in your browser
Search for images using text
Generate code snippets based on your input
Search music by meaning with semantic audio search
Classify images without training data using AI
Upload an image to detect objects
Segment faces in images
In-browser speech recognition w/ word-level timestamps
Generate detailed captions for your images
Classify images in real-time using your webcam
Estimate depth from webcam video in real-time
Generate depth map from an image
Transcribe audio recordings into written text
Transcribe audio to text instantly with WebGPU
Totally Free + Zero Barriers + No Login Required