Skip to the converter
InBrowserConvert

0 bytes uploaded

Files stay on this device

Video to SRT Subtitle Generator (No Upload)

A video to SRT converter that stays in the browser. Pick an MP4, MOV, or WebM, and this subtitle generator writes SRT, VTT, or plain text from the audio track. After the cues are ready, Burn in captions can draw them onto a new MP4 in this tab. The speech model runs here after a one-time download of its weights.

Whisper tiny is about 41 MB of weights (10 MB encoder and 31 MB decoder). Whisper base is about 77 MB (23 MB encoder and 54 MB decoder). The browser downloads the one you pick from Hugging Face the first time, then keeps it in its cache. That download is the model weights, not your file. A speech engine may also load from a CDN.

Model
Save as

Exports an MP4 with the words drawn on the picture. The text is white, with a dark outline and a dark box, along the bottom. Chrome, Edge, and Safari 26 can encode that H.264 file. Firefox and older iOS cannot, and they show an error instead of uploading the video. The subtitle file still downloads.

The model download starts when you transcribe. WebGPU is used when this browser has it. Otherwise the model runs in WebAssembly. iPhone needs Safari 26. Cancel closes the transcriber.

InBrowserConvert Pro (coming soon): batch, bigger files, no limits, still 100% on-device. $29 lifetime or $19/yr.

Subtitles without sending the video away

A video to SRT file from this page is written in the tab. Some transcription sites take the recording onto their server or stop at a free-tier length. Here the file stays on the device, the text has no watermark, and there is no account. Memory is the limit.

Auto subtitles still make mistakes on names, music, and more than one speaker. Read the SRT before you publish it. The page does not claim a perfect transcript.

What the first download is

Whisper tiny is about 41 MB of weights. Base is about 77 MB. Progress during that step names the model, so a network entry for huggingface.co is the weights. The upload meter counts bytes this page sends, and the video is not one of them.

How to convert

  1. 1. Add an MP4, MOV, or WebM

    Drop the video or choose it on this phone or computer. Creating the subtitle file reads the audio track and leaves the picture alone. The file is not sent to a server.

  2. 2. Pick the model, the language, and SRT

    Tiny is about 41 MB of weights. Base is about 77 MB and is slower. Leave the language on Auto, or choose one. SRT is the default. VTT and plain text are on the same page. The weight download starts when you press Create subtitles, and the progress line says it is the model.

  3. 3. Download the subtitle file

    The subtitle file has no watermark. Turn on Burn in captions to export an MP4 with the words drawn on the picture: white text, a dark outline, a dark box, along the bottom, at a size you pick. That MP4 is H.264 and AAC, encoded in this tab. Chrome, Edge, and Safari 26 can encode it. Firefox and older iOS cannot, so they keep the SRT and show an error instead of uploading the video. A phone keeps the decoded audio around 160 MB, and a computer around 400 MB. Cancel closes the job. One file runs at a time. iPhone needs Safari 26. WebGPU is used when the browser has it, and WebAssembly covers the rest.

Questions

Is this a video to SRT converter, free?

Yes. The page is free, with no account and no watermark. Online here means the converter is in the browser. The video stays on this device. A phone still stops around 160 MB and a computer around 400 MB, so the tab is not killed.

Is this a video to SRT file generator?

Yes. The download is an .srt file with numbered cues and timestamps. You can switch the same job to VTT or plain text before you start. Burn in captions can also draw those cues onto a new MP4 when this browser can encode H.264.

Is this an auto subtitle generator, free?

Yes. Whisper tiny or base runs in the browser and writes the cues. The first run downloads the model weights. That transfer is the model, not your video. The header should stay at 0 bytes uploaded.

Can I transcribe video to SRT free?

Yes, for an MP4, MOV, or WebM that has an audio track. There is no sign-up and no daily quota. A long video can still fail when this device runs out of memory. A silent file produces an empty subtitle file.

Is this a subtitle generator for video?

Yes. It is aimed at a video file, and it listens to the audio track. Chrome and Edge can read these files. iPhone needs Safari 26. Older iOS shows an error and does not upload the video. Firefox can write the SRT when it can decode the audio with WebCodecs. Burning the words into an MP4 needs Chrome, Edge, or Safari 26, because Firefox cannot encode H.264 here.

Does it work on iPhone?

In Safari 26 or newer, which can decode the audio track. The model then runs in the browser, with WebGPU when Safari exposes it and WebAssembly otherwise. Older iOS shows an error and does not upload the video. A phone also uses the smaller file ceiling, about 160 MB.

Which files does this page actually accept?

MP4, MOV, and WebM. The subtitle download is SRT, VTT, or TXT. Burn in captions adds an MP4 with the words on the picture when the browser can encode H.264. Other video types are refused, and they are not uploaded. A video with no audio track stops with an error.

Can I burn the subtitles into the video?

Yes, after the cues are ready. Burn in captions draws them on the picture and saves a new MP4 in this tab. The text is white, with a dark outline and a dark box, along the bottom. You can change the size. Chrome, Edge, and Safari 26 can encode that H.264 file. Firefox and older iOS cannot, so they keep the subtitle file and show an error instead of uploading the video.

Where do the model weights come from?

From Hugging Face, the first time you transcribe: onnx-community/whisper-tiny or onnx-community/whisper-base, quantized. The speech engine’s WASM file can load from jsDelivr. This site does not host those files, and neither download is your video. The browser cache keeps the weights for the next visit.

Related tools