AI Tools

Blur only the background of a portrait; AI finds the person on your device and nothing is uploaded.

Replace a portrait's background with transparency, a solid colour or your own picture, on your device.

Get a transparent person cut-out, a person mask and a background mask from portraits, made on your device.

Create a grayscale depth map from a single photo with Depth Anything V2, on your device.

Select any object in a photo by clicking it with Segment Anything (SlimSAM); save the mask or object as PNG.

Paint over unwanted objects, people or text and let AI fill the area, on your device.

Colourise old black and white photos with natural colours using DDColor, privately on your device.

Reduce grain, low-light noise and JPEG artefacts with a restoration model that runs on your device.

Repair edges and fine detail with a lightweight super-resolution model, then sharpen lightly, normally or strongly.

One-click enhancement: remove noise, repair detail and upscale photos ×2 or ×4.

Detect 33 body keypoints from a photo or your camera and draw the pose skeleton, on your device.

Track 21 points per hand in real time from your camera; see left/right hand, finger states and FPS.

Recognise open palm, fist, thumbs up/down, victory, pointing up and 'I love you' gestures live.

Detect 478 face landmarks from a photo or camera and draw the outline, eyes, brows, nose and lips.

Classify visible facial expressions (happy, sad, angry, surprised, neutral, fear, disgust) with confidence scores.

Detect speech, music, dogs, sirens, rain, vehicles, applause and 500+ sounds with a timeline, on your device.

Find where people speak and where it's silent, with timestamps, totals and an exportable segment list.

Estimate a song's tempo (BPM) with beat markers and half/double-tempo alternatives.

Estimate a song's key (e.g. A minor or C major) with confidence, relative key and Camelot code.

Remove fan, hum, traffic and room noise from voice recordings with RNNoise; compare and download a clean WAV.

Turn speech in videos into timed subtitles with Whisper, privately on your device; save as SRT, VTT or TXT.

Remove background noise from speech in videos; the picture is copied as-is and only the audio is cleaned.

Generate short, accessibility-focused alt text and an optional detailed description for images, on your device.

Turn a photo into a short, detailed or very detailed description with a vision-language model on your device.

Upload a PDF, TXT or Markdown file and ask questions; the document is parsed, indexed and answered on your device.

Compare two sentences or short texts by meaning, not words, using sentence embeddings on your device.

Highlight people, organisations, places and other names in English text with confidence scores and CSV export.

Classify the emotions expressed in English text: joy, sadness, anger, fear, surprise, neutral and more.

Find a code snippet's programming language among 107 languages, with confidence and alternatives.

Turn English articles and long texts into short, medium or detailed summaries without sending the text anywhere.

Extract printed text from photos, screenshots and scans with Tesseract OCR running on your device.

Recognise text mixing up to three languages, including Latin, Cyrillic, Greek, Arabic, Hebrew, Hindi, Chinese, Japanese and Korean.

Translate text between English and 23 languages with OPUS-MT models on your device; nothing goes to a translation server.

Turn English text into natural speech with 14 American and British voices, adjustable speed and WAV download.

Chat with a small AI model that runs entirely in your browser; nothing you type is sent to a server.