AI tools

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.

An alt text generator that looks at the photo and writes the first draft, using Microsoft's Florence-2.

Audio transcription with Whisper. Drop in a recording and get editable text, plus SRT and WebVTT carrying timestamps, from any of four model sizes.

Remove the background from a photo and keep a transparent PNG, or set the cut-out on a solid color as a JPEG. It finds the subject itself, or you tap or circle the one you want.

Blur, pixelate or black out faces in a photo. A small detector boxes the faces it finds, small ones in a group included, and you box whatever it misses.

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.

Remove a photobomber, a bin or a stray cable from a photo. Tap it, circle it or paint over it, see how much of the frame it takes, and MI-GAN fills the gap.

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.

Paraphrase text four ways: formal, casual, shorter, or longer, with a small language model that does the rewriting on your own graphics card.

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.

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.

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 a PDF in ordinary words. Answers cite the page and show a snapshot of the passage they came from.

Remove background noise from audio with DeepFilterNet, a speech model that runs on your device. Hum, fans and hiss drop away, the voice stays, and the clean take saves as M4A, WAV, Opus or FLAC.

Text to speech two ways: the voices your device already has, or a 13-voice English model that hands you a file.