# Get an SRT file from any video > AI transcribes your video in the browser and gives you a timestamped SRT file — the format every player and editor accepts. Nothing is uploaded. Auto-generate accurate SRT, VTT, or plain-text subtitles from any video or audio using OpenAI's Whisper speech-recognition model running in the browser (WebGPU or WebAssembly), across roughly 100 languages — or upload your own SRT/VTT. From there you can download the file, burn styled TikTok-style captions permanently into the video, or add a soft subtitle track viewers can toggle on and off. Nothing is uploaded; handles up to 1 GB / 2 hours of audio. ## SRT subtitles without uploading your footage Most "SRT generator" sites make you upload your video to their servers and wait in a queue. This one runs OpenAI's Whisper speech-recognition model directly in your browser — the model downloads once and every file after that is transcribed on your own hardware. Nothing is uploaded, which matters for client work, interviews, unreleased footage, or anything under NDA. The result is a standard timestamped .srt you can hand to any platform or editor. On a machine with GPU acceleration it transcribes several times faster than real time, and formats and caption lengths switch instantly afterward without re-processing. ## Frequently asked questions ### What is an SRT file? SRT (SubRip) is the universal subtitle format: numbered, timestamped text blocks that YouTube, Premiere Pro, DaVinci Resolve, CapCut, VLC, and virtually every player and editor read directly. This tool produces a clean, standards-compliant .srt. ### Can I edit the timing or wording? Yes. The SRT is plain text, so you can open it in any editor to fix a word or nudge a timestamp. You can also switch caption length (full sentences down to word-by-word) before downloading, and copy the whole transcript to your clipboard in one click. ### Can I use subtitles I already have? Yes. Upload an existing SRT or VTT file to skip transcription — then download it in another format, burn the captions into the video, or add them as a soft track. ### Do you upload my video? No. The Whisper AI transcription runs locally in your browser via WebGPU or WebAssembly, and if you burn captions in, that re-encode runs on your device too. Your file never leaves your computer — once the page has loaded it even works offline. ### What languages are supported? Whisper was trained on about 100 languages, including English, Spanish, Catalan, French, German, Chinese, Japanese, Arabic, and Hindi. Pick the spoken language from the grid before transcribing (English is the default) so it transcribes accurately. ### Why does the first file take longer? The Whisper speech model (~77–150 MB depending on your browser) downloads the first time you use the tool and is then cached. After that, transcription starts immediately. ### Is it really free? Yes. The subtitle generator is completely free, with no signup, watermarks, or limits. We make money from our video translation service, not from this tool. --- _Free · No sign-up · No watermark · Runs entirely in your browser — your file never leaves your device._ - Open this tool: https://easydub.video/tools/subtitles/srt-from-video - All free EasyDub tools: https://easydub.video/tools