Free SRT Subtitle Generator from Video
Generate .srt and .vtt subtitle files from any video with on-device AI, then fine-tune every line in the timing editor. Built for YouTube uploads and online courses — free, no signup.
Drop a video here or click to browse
MP4, WebM or MOV. Used for preview only — nothing is uploaded.
Drop a .srt / .vtt file or click to browse
Edit timings of a file you already have.
| # | Start (s) | End (s) | Text | Actions |
|---|
Merge joins a row with the next one · Split divides a row at its middle word · times are in seconds.
How to use the SRT subtitle generator
- Upload or transcribeDrop in your video and press Transcribe (the AI model downloads once, ~40 MB) — or open an existing .srt / .vtt file to edit it.
- Fix timings and textEdit any row, merge, split, delete, add rows, or shift everything at once. Watch the live preview to check sync.
- DownloadExport the finished .srt for YouTube or .vtt for web players — free, no signup.
Try the editor with sample subtitles
No video handy? Load a sample and practice the timing editor:
Frequently asked questions
What is the difference between this and the Auto Captions tool?
This page produces subtitle FILES (.srt and .vtt) that you upload to YouTube, Vimeo, or a course platform — the viewer can toggle them on or off. The Auto Captions tool burns animated, always-visible captions directly into the video file itself, which is better for TikTok, Reels, and Shorts.
Where does the AI transcription happen?
On your device. The first time you press Transcribe, the Whisper speech model downloads once (about 40 MB) from HuggingFace’s CDN — after that one-time download, everything runs locally in your browser. Your video is never uploaded to any server.
Can I fix timings and text after transcription?
Yes — that is the point of this tool. Every subtitle row is editable: change start/end times, rewrite the text, merge two rows, split one row, delete rows, add new ones, or shift all timings at once to fix a sync offset.
How accurate is the transcription?
It is an AI draft tuned for clear English speech — good enough to save you most of the typing, but always proofread before publishing, especially names, numbers, and technical terms. The timing editor makes corrections fast.
Need another video tool?
Scripts that sell, captions without watermarks, silence removed and more — 15 free tools that run entirely in your browser.