Transcribe an MP4 video

Choose a video file and only its audio track is extracted and transcribed. The video itself is never uploaded. The result plays back as captions over the video, and you can export it as SRT subtitles.

Checking your environment…

Model

Language

Speaker diarization

Speakers (0 = auto)

You can normally leave this on Auto. Change it only if the result clearly has the wrong number of speakers

Drop audio or video files, or click to choose (multiple files OK)

MP3, WAV, M4A, FLAC, MP4, MOV, MKV and more (no file size limit)

Choose an SRT or VTT subtitle file to edit and translate it without transcribing (choose a video with it to check while it plays)

Your file is never sent outside the browser

No file? Record with your microphone. Transcription starts after you stop recording (up to about 000 min on this device with the selected model). Your recording is not sent to any server either.

How to transcribe an MP4 video

Set the model, language and speaker diarization first, because transcription starts as soon as the video is loaded. For videos with background music or sound effects in languages other than Japanese, Chinese and Korean, choose Small or a larger model.
Drop the video file here or click to choose it. The audio track is extracted inside your browser as well, and lines appear on screen as soon as they are finalized.
When it finishes, play the video and correct the wording and timing while the result runs as captions. Then export it under "Download" as SRT or VTT subtitles, or as a TXT or Word document. What to check before using it as subtitles is covered on the Subtitle (SRT) generation page.

Loading different kinds of video

Videos shot on a smartphone load as they are once you move them to your computer. Videos from the iPhone camera are saved as MOV, which works the same way as MP4. You can also open this page in your phone's browser and choose the video there, but it then runs in a reduced-memory mode (WASM) and can process shorter lengths at once than a computer. Load long videos on a computer.
Videos on YouTube and other video sites cannot be loaded from their URL. For a video you uploaded to YouTube yourself, select it under "Content" in YouTube Studio and choose "Download" from its menu to save it as MP4. Then choose the saved file on this page.
For a video in another language, choose that language under "Language" before loading the file. When it finishes, use "Translate" in Chrome or Edge on a computer to play the translation as captions over the video.
When you add subtitles in video editing software, load the video you exported after editing. If you transcribe the raw footage instead, the subtitle timing drifts from the finished video by however much you cut. Export SRT to load it into video editing software, or VTT for a video player on a web page.

How video transcription works here

Only the audio is extracted, so resolution and video codec make no difference to the result. Videos with no audio track cannot be processed. Loud background music or ambient noise does reduce accuracy — for such material, normalise the volume beforehand, and for languages other than Japanese, Chinese and Korean, use the small model or larger.

When transcription finishes, the result is overlaid on the video as captions during playback. Fix the wording while you watch, or switch to translated captions with the translate function. Besides subtitles (SRT, VTT), you can export plain text (TXT), Word, PDF and more. SRT carries timecodes, so it loads directly into video editors or YouTube. With speaker diarization enabled, each line also records who was speaking.

For online meeting recordings such as Zoom or Teams, the steps are on the Meeting transcription page.

If something goes wrong

If it stops with an error, check that the video actually contains audio. Screen recordings made with the microphone and system audio turned off have no sound.
Videos of several gigabytes load fine, but the whole file has to be read to extract the audio, so processing takes a while to start. If the video is on an external drive or a network folder, copying it to your computer's internal drive first makes it start sooner.

Frequently asked questions

Which video formats are supported?

MP4, MOV, MKV, WebM, AVI, WMV, FLV, MPG, MPEG-TS and 3GP. In every case only the audio track is extracted for transcription.

Is the video file really not uploaded?

Correct. Reading the video and extracting its audio both happen inside the browser, so the file never leaves your device. Processing statistics used to fix problems (device specs, error type and similar) are sent to this site's own server, but they contain no audio, transcript text, file names or IP addresses. You can stop this by turning off the switch under “Help us improve the service” at the bottom of the page.

Can I use the result as a subtitle file?

Yes. Exporting as SRT produces timecoded subtitles that video editors and YouTube can load directly. Before exporting, play the video to check the caption text and timing on screen and correct the wording.

Can it handle long videos?

Yes. There is no limit on file size or duration. How long a video can be processed at once depends on your device's memory and the selected model; if it does not fit, the page tells you before processing starts. The tab does need to stay open while processing runs.

Getting the audio ready, and after transcribing

MP3 transcriptionPick an MP3 file and turn it into text.M4A transcriptionTurn M4A files, such as iPhone voice memos, into text.Subtitle (SRT) generationGenerate timecoded subtitles from audio or video.Transcription with Whisper AIUse Whisper to transcribe without installing anything.Meeting transcriptionTurn meeting recordings into minutes, split by speaker.Recording transcriptionTurn voice recorder files and long recordings into text.See all featuresTranscribe audio and video files entirely in your browser. No account and no upload — your audio never leaves your device. Free with no time or usage limits. Whisper AI transcription of MP3, WAV, M4A, MP4 and more, plus speaker diarization and SRT subtitle export.

Help us improve the service

Sending us the circumstances of a run — successful or failed — helps us track down problems (a failure rate needs both). Knowing which devices and settings fail most often lets us revise the recommended defaults and fix the bugs behind them. If you don't mind, leaving this on is a real help.

What is sent

Your device specs (GPU model, memory, core count), browser and OS, the model and language you chose, your speaker diarization setting (on or off, and the number of speakers you set), the page's display language, how far the run got (including when you stopped it or closed the page), the error type and details, the file's format with a rough size and length, and how long it took. A temporary number that links runs in the same tab (it is deleted when you close the tab). On the result screen: how many times you used editing (such as renaming speakers or splitting lines), translation, summaries and subtitle imports, the formats you chose under “Download”, how often you used “Copy text” and “Download all”, and the translation language pair.

What is never sent

Audio, transcripts (including speaker names and translations), file names, and IP addresses. The data goes only to this site's own server, never to a third-party service.

Sending