Subtitle Generator
Generate subtitles for your videos automatically and for free — Whisper AI listens to the audio and creates time-coded SRT or VTT captions, ready for YouTube, Vimeo, Premiere Pro, DaVinci Resolve, CapCut and web players. Translate captions to English, set the line length, and edit before you download. Runs privately in your browser.
100% private — transcription runs on your device. Conversion happens on your device; nothing is uploaded.
Transcription runs on your device with OpenAI’s open-source Whisper model — your audio is never uploaded. The model downloads once (40–250 MB) and is then cached by your browser. A fast computer with a modern browser (Chrome or Edge, ideally with WebGPU) transcribes an hour of audio in a few minutes; older devices are slower. Always check names and numbers.
How to generate subtitles for a video
- Drop your video (or its audio) in the box.
- Choose the spoken language and accuracy.
- Click Generate subtitles.
- Check and edit the captions, set the line length, then download SRT or VTT.
What you can use it for
- Add captions to YouTube, Instagram and TikTok videos
- Make videos accessible for deaf and hard-of-hearing viewers
- Create English subtitles for foreign-language videos
- Import captions into Premiere Pro, Final Cut, DaVinci Resolve or CapCut
More free tools
Designing with text?
Style, caption and decorate text with our free, private text and image tools.
See all free tools →Frequently asked questions
How do I add the subtitles to my video?
Download the SRT file and upload it with your video on YouTube (Subtitles → Upload file), Vimeo or Facebook, or import it into your editor. Use VTT for HTML5 video players on websites.
SRT or VTT?
SRT is the most widely supported subtitle format for platforms and editors. VTT (WebVTT) is the standard for <track> elements in web video players.
Which languages are supported?
Whisper understands about 100 languages. The menu lists the most common ones; “Detect automatically” works for the rest. You can also translate speech in any supported language straight into English text.
Is my audio uploaded?
No. OpenAI's open-source Whisper model runs inside your browser. The model is downloaded once (40–250 MB) and cached; your audio never leaves your device.
How long does it take?
On a recent laptop with Chrome or Edge, an hour of audio takes a few minutes with the Balanced model (faster with WebGPU). Older phones and computers are slower — try the Fast model.
How accurate is it?
Clear speech with little background noise is transcribed very well. Accents, crosstalk, music and technical terms reduce accuracy — always check names and numbers before publishing.
Can I burn the subtitles into the video?
This tool creates subtitle files. To burn them in permanently, import the SRT into a video editor such as CapCut, DaVinci Resolve or Premiere Pro.
Which video and audio files can I use?
You can drop or browse for MP4, MOV, WebM and MKV video, or MP3, WAV, M4A, AAC, OGG and FLAC audio. Only the sound track is used, mixed down to one channel, and your browser does the decoding, so a format can work in one browser but not another. If you see “No audio could be read from this file”, the file may have no sound or use a codec your browser can't decode; try Chrome or Edge.
Which Accuracy setting should I choose?
Balanced (Whisper base, about 80 MB) is selected by default and is a sensible place to start. Fast (Whisper tiny, about 40 MB) is the smallest and quickest, which helps on older phones and computers. Best (Whisper small, about 250 MB) is the largest and slowest; try it when the captions miss words. Each model downloads the first time you use it and is then cached by your browser.
What does Max characters per line do?
It sets the line length for SRT and VTT captions. The default is 42, and you can choose any number from 20 to 80. When a caption's text is longer than your limit, it is split into two lines of roughly equal length, so a caption never runs to more than two lines. The result box updates as soon as you change the number, so you can check the layout before you download.
Can I edit the subtitles before I download them?
Yes. The result box is editable, and Download and Copy both use whatever is in it, so you can fix names, spelling and punctuation. Choose the format and line length first, then make your corrections: changing either setting rebuilds the captions from the original transcript and replaces your edits. Check names and numbers against the video before you publish. The file is named after your video, such as interview.srt.
Can I use the subtitles commercially, and do I need an account?
No account or sign-up is needed. The subtitles are made from your own video on your own device, and you can use them however you like, including on commercial videos, with no credit needed. The Whisper model weights the tool runs are released under the Apache-2.0 licence. Just make sure you have the rights to the video and its audio, especially if it features other people's speech or music.