Video to SRT

Drop a video and get an SRT subtitle file of everything that's said, timed to the speech. It's transcribed on your device, so the video never leaves your computer.

Transcribed on your device by an AI speech model. Your file is never uploaded.

Subtitles in three steps

1.

Drop your video

MP4, MOV, WebM, MKV or AVI, up to 30 minutes.

2.

Pick the language

Or leave it on automatic detection.

3.

Generate and download

Preview the subtitles on your video, then download the SRT.

What you get

A standard SRT file: numbered subtitles with start and end times, split into lines of up to 42 characters (you can change that) and two lines per subtitle, the format YouTube, Premiere Pro, DaVinci Resolve, CapCut and every major player accept.

Upload it to YouTube as a subtitle track, import it into your editor to burn it in, or drop it next to the video with the same file name so VLC loads it automatically.

How the transcription works

Transcription is done by Whisper, the open-source speech recognition model from OpenAI, running inside your browser. The model downloads once (40 to 250 MB depending on the accuracy you pick) and is cached, so later files start straight away. Your video is never uploaded.

With a recent Chrome or Edge on a computer with a graphics card, it runs on the GPU and takes a fraction of the video's length. Without one it runs on the CPU, which can take about as long as the video itself. Files up to 30 minutes work.

Whisper understands about 100 languages and adds punctuation. Accuracy is good on clear speech, and lower with music, heavy accents or several people talking at once: check names and numbers before you publish.

Caption your videos in minutes

Animated, word-synced captions in the styles top creators use. Upload a video, pick a style, fix any word, and export.

Frequently
Asked Questions

How do I get an SRT file from a video?

Drop the video above and press Generate subtitles. The speech is transcribed and timed, and you download the result as an .srt file.

Is the video uploaded to a server?

No. The speech model runs in your browser, so the video stays on your device.

How long does it take?

On a computer with WebGPU (recent Chrome or Edge) usually well under the video's length; on the CPU, about as long as the video.

Which languages work?

About 100, including English, Spanish, Portuguese, French, German, Hindi, Arabic, Japanese and Chinese.

Related tools