AI tools
Free AI tools that run on your device, not a server — remove image backgrounds, pull text from scans, blur faces, and more, with no account, upload, or limits.
- Add Subtitles to Video (Burn-In)
Add subtitles to a video permanently. Load an SRT or VTT, or let Whisper write one from the speech, then style the captions on a live preview and export an MP4 with the words on every frame.
- AI Alt Text Generator
An alt text generator that looks at the photo and writes the first draft, using Microsoft's Florence-2.
- AI Audio Transcription
Audio transcription with Whisper. Drop in a recording and get editable text, plus SRT and WebVTT carrying timestamps, from any of four model sizes.
- AI Background Remover
Remove the background from an image and get a transparent PNG back, or drop the cut-out onto a solid color. Auto finds the subject, or you tap the one you want.
- AI Face Blur
Blur faces in a photo, or pixelate them. A detector boxes the obvious ones, and you drag a box over whatever it misses.
- AI Image Upscaler
AI image upscaler that enlarges a photo 2× or 4×, or works back from the exact print size you type in. Rebuilds detail instead of stretching pixels.
- AI Object Remover — Magic Eraser
Magic eraser for photos: brush over a photobomber or a power line and an on-device MI-GAN model repaints the gap using the pixels around it.
- AI OCR — Image & PDF to Text
Extract text from an image or a scanned PDF, using a neural engine that reads 50 scripts and copes with a page shot at an angle.
- AI Paraphraser
Paraphrase text four ways: formal, casual, shorter, or longer, with a small language model that does the rewriting on your own graphics card.
- AI Text Summarizer
Summarize a long article, an email thread, or a report down to a few sentences. Pick short, medium, or long; the AI model downloads once and then works offline.
- AI Video Subtitle Generator
A video subtitle generator built on Whisper. Feed it an MP4 and get SRT, WebVTT or a plain transcript, with cues capped at two lines of 42 characters.
- AI Vocal Remover — Split Vocals & Instrumental
A vocal remover that splits a song into two stereo tracks, the voice on one and the instrumental on the other, using Deezer's Spleeter model.
- Chat with PDF
Chat with a PDF in ordinary words. Answers cite the page and show a snapshot of the passage they came from.
- Remove Background Noise from Audio
Remove background noise from audio with DeepFilterNet, an 8.6 MB speech model. Hum, fans and chatter drop away, the voice stays, and the clean take saves as M4A, WAV, Opus or FLAC.
- Text to Speech
Text to speech two ways: the voices your device already has, or a 13-voice English model that hands you a file.
Modern AI usually means uploading your file to someone's server and waiting on an account, a credit balance, or a daily cap. These tools take the opposite route — the model runs on your own machine, so your audio, text, and images never leave the browser tab. Open one, hand it your input, and the answer is computed locally.
The trade-off is stated plainly: the first time you open a tool it downloads its model once — a few tens to a few hundred megabytes, depending on the job — then caches it so every later run is instant and works offline. On-device models are smaller than the cloud giants, so they aim for quick, practical results rather than matching a frontier chatbot, and each tool spells out what it does well.