Free · No signup · Nothing uploaded
Automatic subtitles, word by word
Turn speech into accurate captions with timing for every word, right inside our video editor: captions sit on the timeline, and every word can have its own style.
Upload a video to add captions
Captions are made on your device, then you edit and style them, word by word, in the editor.
Word-Level Automatic Subtitles: free, private and right in your browser
Turn speech into accurate captions with timing for every word, right inside our video editor: captions sit on the timeline, and every word can have its own style.
- Word-level timing from on-device AI
- 99 languages, auto-detected, or translate to English
- Captions on the editor timeline
- Style, move and animate single words
- Burn into MP4/WebM or download SRT, VTT, TXT
How to use the word-level automatic subtitles
REC 00:42Step 01Upload your video
Choose an MP4, MOV, WebM or MKV file (or an audio file). It opens in the editor.
🇪🇸 Spanish ▾Haz clic para empezarStep 02Generate captions
Pick the language and quality, then press Generate. Captions appear on the timeline; drag them to move, pull an edge to retime.
MOV → MP4Step 03Style and export
Choose a caption style, click any word on the video to give it its own size, color or position, then export the video or an SRT/VTT file.

TikTok, Reels and Shorts
Most people watch without sound: big animated captions keep them watching.

Accessibility
Make videos usable for deaf and hard-of-hearing viewers.

Courses and interviews
Caption long talks and get a transcript at the same time.
Frequently asked questions
Is my video or audio uploaded?
No. Speech recognition and every edit run in your browser on your own device. Nothing is sent to a server.
Why does it download something the first time?
The speech model (41 to 250 MB, depending on the quality you pick) is downloaded once and kept by your browser, so next time it starts immediately. Your files are never sent anywhere.
Which languages are supported?
Around 99 languages, including English, Spanish, Hindi, French, German, Portuguese, Japanese, Chinese and Arabic. The language is detected automatically, or you can choose it. You can also translate the speech into English captions.
What if a word is wrong?
Click the word and type the fix. Its timing stays the same, so word-by-word caption styles still line up. Find & replace fixes a name everywhere at once.
Is there a watermark?
Free videos get a small VIDEOTOURO.COM mark in a corner, added only when you export (you never see it while editing). Subtitle files (SRT, VTT, TXT) never have one.
Guides
Step by step
Tools
