Will the SRT work in YouTube Studio and Premiere?

Yes — the output is standard SubRip: numbered cues with comma-decimal timestamps. YouTube, Premiere, Resolve, Final Cut (via import), CapCut and VLC all accept it directly.

My video is under NDA — is this safe to use?

The video is processed entirely on your device; neither the file nor the subtitles ever reach a server. That's the whole point of building this client-side.

Can I edit the subtitles before downloading?

The preview box shows the full SRT — copy it, adjust any cue, and save it as a .srt file; or download first and edit in any text editor or your video editor.

How do I get the subtitles to show on the video itself?

Import the SRT into your video editor as a caption track and export the video; most editors can burn it in. Alternatively upload the SRT alongside the video on YouTube or Vimeo, where viewers can toggle it.

Does it work with several speakers in the video?

Yes, the speech is transcribed regardless of who is talking, but cues are not labelled by speaker. Add names or dashes manually while reviewing if viewers need to tell voices apart.

Video to SRT — Generate an SRT File From Video Free

Convert MP4, MOV or WebM into a clean .SRT subtitle file with AI — private, free, no watermark.

Model

Spoken

Output

🌍 The spoken language is detected automatically and the transcript comes out in that same language. Set it manually above if your audio is hard to hear, and use Output to translate into English.

⬇️ One-time download: 104 MB (Accurate model 73 MB + 31 MB audio engine, shared with the video tools) — only the first time: it stays saved in your browser, so next time it starts right away. (Translating or switching model needs its own file; a browser can clear this cache if storage runs very low.) Processing takes about 4-8 min per 10 minutes of audio on a typical laptop.

What exactly is downloaded — and is it safe?

• The speech model is OpenAI's Whisper, open source, converted to run in browsers. The audio engine is FFmpeg, the open-source tool behind most video software.
• They come from Hugging Face and unpkg — public repositories used by researchers and developers worldwide, not from us.
• They are not programs. Nothing is installed, no permission is asked, and your browser keeps them in its own cache exactly like it keeps a website's images.
• They can't read your files or touch anything outside this page. Remove them any time by clearing this site's data in your browser.
• Your audio never goes the other way: this site has no server receiving files.

Drop your video or audio here or click to choose

transcribed on your device by OpenAI's Whisper — your recording is not uploaded

ℹ️ Use a recording on your device that you own or have permission to process. This tool cannot fetch YouTube or social video links. Start with a short clip. Larger models can improve accuracy but require more memory and download data. Processing time varies by device, model and recording length. Always review the result.

An SRT file is the plainest subtitle format there is: a number, a start and end time to the millisecond, the text. YouTube Studio, Vimeo, Premiere, Resolve, Final Cut and VLC all read it, which is why a client or a platform asks for "the SRT". This page generates one from an MP4, MOV, WebM or MKV using OpenAI's Whisper running in your browser, so the footage is transcribed on your device and never uploaded.

That matters for the videos that most need captions: an ad before launch, an internal training film, an interview recorded under an NDA. The captions come back as timed cues you can preview, copy and edit before downloading; VTT is available if a web player needs it instead.

Honest scope. This produces a separate subtitle file, not a video with subtitles burned in, and it does not touch the footage; to show captions permanently in the picture you load the SRT into your editor and export from there. The timestamps are a good draft, not a finished edit: review spelling, names, numbers, line length and the cue timing around fast dialogue. The first run downloads the processing files, and an hour of footage is a serious task for an older laptop, so start with a short clip.

More sizes & options

Subtitle Generator — all options

Frequently asked questions

Will the SRT work in YouTube Studio and Premiere?: Yes — the output is standard SubRip: numbered cues with comma-decimal timestamps. YouTube, Premiere, Resolve, Final Cut (via import), CapCut and VLC all accept it directly.
My video is under NDA — is this safe to use?: The video is processed entirely on your device; neither the file nor the subtitles ever reach a server. That's the whole point of building this client-side.
Can I edit the subtitles before downloading?: The preview box shows the full SRT — copy it, adjust any cue, and save it as a .srt file; or download first and edit in any text editor or your video editor.
How do I get the subtitles to show on the video itself?: Import the SRT into your video editor as a caption track and export the video; most editors can burn it in. Alternatively upload the SRT alongside the video on YouTube or Vimeo, where viewers can toggle it.
Does it work with several speakers in the video?: Yes, the speech is transcribed regardless of who is talking, but cues are not labelled by speaker. Add names or dashes manually while reviewing if viewers need to tell voices apart.

Guides

Related tools

🔒 Private mode (the default): your recording never leaves your device. Instant mode is optional, you switch it on yourself, and it sends the audio to the browser's speech service.