Do I need to extract the audio first?

No. Upload the MP4 as it is. Converting it beforehand only costs you time and, if you re-encode, a bit of quality.

What if the MP4 has no audio track?

Then there's nothing to transcribe and we tell you so instead of charging you for silence.

Does the resolution matter?

Not at all. 4K or 480p, what we read is the audio. Resolution only affects how long the upload takes.

Can I get an SRT out of it?

Yes, from the same transcript, with the timings already lined up with the video.

Do I have to convert the MP4 first?

No. Upload it as it is and we read the audio track inside. Converting first only makes sense if you want to upload fewer megabytes over a slow connection.

What if the video has no sound?

We tell you as soon as we check, and no minutes are spent. It usually happens with screen recordings where the microphone was off.

Try it without an account

Transcribe an MP4 file

Drop the MP4 and get the text. We read the audio track inside it — no converting, no extracting, no extra software.

Drag your file here

MP3, WAV, M4A, MP4, MOV… up to 10 GB

Straight from the MP4, no extracting first
Up to 10 GB per file, hours of recording
Text, subtitles or both from the same pass

MP4

What this tool does

An MP4 isn't a video: it's a box with a video track and an audio track inside. Transcribing it means reading the second one, and that happens on our side the moment you upload it.

It's the format every phone, every screen recorder and every meeting app writes, which is why it's the file most people arrive here with. Whatever's inside — AAC, MP3, or the odd one your camera chose — we read it.

What we handle that others don't

The audio codec inside doesn't matter: AAC, MP3, ALAC or PCM all get read.
The timestamps match the video, so a line clicks straight to its moment.
Speaker separation, which on a recorded call is what makes it readable.
No file conversion on your machine and no software to install.

How it works

1
Drop the MP4
Recorded on a phone, exported from an editor or downloaded from a meeting app.
2
We read the audio inside
With speakers separated when there's more than one voice.
3
Read it or subtitle it
The text as DOCX or PDF; the subtitles as SRT or VTT, timings included.

What people use it for

Zoom and Teams recordings

They come out as MP4. This is the shortest path from that file to minutes.

Phone video

A talk, a class, an interview filmed on a phone. Straight from the gallery.

Screen recordings

A demo or a walkthrough turns into a written script you can edit.

In detail

The MP4 that comes out of a meeting

Zoom, Meet and Teams hand you an MP4 when you record a call, and they're among the files that come out best: each person speaks into their own microphone, there's no room noise, and voices overlap far less than they do in a room. If you recorded with separate tracks as well, speaker separation gets it right nearly every time.

Size is the only surprise: an hour of meeting recorded in high definition easily reaches two or three gigabytes because of the picture, which isn't used here for anything. You can upload it as it is — the limit is 10 GB — or pull the audio out first, which leaves you with about 50 MB.

Phone video, vertical, handheld

Also fine, and more common than you'd think: interviews shot on a phone, statements, whole lectures. Orientation and resolution are irrelevant because the picture never enters the process; the only thing that counts is where the microphone was.

One piece of advice changes the result more than any setting: if you're recording a conversation on a phone, put it near whoever is talking rather than in the middle of the table. Half a metre shows up more in the transcript than any option you could tick here.

Questions

And if what you have is the video?

Upload it and you'll get the transcript with timestamps, the speakers separated by name and a summary with the key points. You can start without an account.

Transcribe my recording See prices

Related tools

Worth reading

What is an SRT fileWhat's inside a .srt, why it's still the default subtitle format after thirty years, and the four mistakes that stop one from loading.