Free tools

Free video tools that never upload your files

Single-file video tools that run entirely in your browser. The AI models download to your computer and process the video there, so there is nothing to sign up for, no watermark and no server ever sees your footage.

AI video describer Splits a video into scenes and writes a plain-English description of each one with a vision model running in the browser. Exports TXT, SRT or WebVTT. No upload. Find a moment in a video Type what you are looking for and AI finds the matching moments in a video, with timestamps, by looking at the picture rather than the file name or a transcript. No upload. Video background remover Cuts the person out of a video with an AI matting model in the browser and puts them on transparency, a solid colour or a blurred background. Keeps the sound, no watermark, no upload. Remove logo from video Mark the logo, date stamp or caption in your own footage and an inpainting model fills that area on every frame, keeping the sound. Best for marks that stay in one place. No upload. Video to text Transcribes speech in a video or audio file with OpenAI Whisper running locally in the browser, with timestamps. Exports TXT, SRT and WebVTT. No upload, no sign-up. Caption generator Generates captions for a video with Whisper in the browser, splits them into short readable lines, lets you edit them on a live preview and exports SRT, VTT or a video with the captions burned in. No upload. Extract frames from video Finds the scene changes in a video, or samples it every N seconds, and saves full-resolution JPG or PNG stills as a ZIP. Runs in the browser, no upload. Add caption to GIF Puts a caption on an animated GIF or a short clip: white caption bar, top and bottom meme text, or subtitles. Live preview and GIF export in the browser, no watermark.

Why these tools run in the browser

Most free online video tools upload your file, process it on a server and send the result back. That is slow for large files, it is why so many of them cap the length or add a watermark, and it means the footage sits on somebody else's disk. These tools use the video decoder built into your browser and open AI models (Whisper for speech, Florence-2 and CLIP for pictures, MODNet and MI-GAN for cutting out and filling in) running through WebGPU or WebAssembly. Once a model has downloaded, you can disconnect from the internet and they keep working.

When one file at a time is not enough

They are built by the team behind Reelary, a desktop app that does the same things across a whole footage library: it transcribes and describes every clip, lets you search all of it by meaning ("drone shot of a coastline at sunset", or a line someone said), and assembles the results into a cut. It also runs entirely on your own machine. Download Reelary free for Mac or Windows, or read how local AI video search works.