Do I have to extract the audio first?

No. We extract the audio automatically. Doing it manually only adds time and can reduce quality.

Is the whole video uploaded?

Yes. It's stored on European Union servers and deleted automatically after 14 days, or 90 with a paid plan. If you'd rather not upload the video, you can extract the audio first with our dedicated tool.

Which video formats are supported?

MP4, MOV, MKV, AVI, WEBM, WMV, FLV and M4V. What matters is the internal audio track, which is supported in every case.

Can I get subtitles instead of text?

Yes. The same transcript can be downloaded as SRT or VTT with the timings already calculated.

Is the whole video uploaded?

Yes, the entire file, up to 50 GB. If you'd rather upload less data, extract the audio first with our video-to-audio tool: you get the same result with a file ten times smaller.

Does it work with screen recordings?

Yes, without issue. Recorded meetings and lectures are among the most common uses, and they often give better results than in-person recordings, since each voice comes from its own microphone.

No account required

Turn a full video into text

Upload the video as is. We extract the audio, transcribe it, and hand you the text with timestamps and every voice identified.

Drag your file in here

MP3, WAV, M4A, MP4, MOV… and any other audio or video, whatever the size

Accepts MP4, MOV, MKV, AVI, WEBM and other common formats
Timestamps synchronised with the video
Subtitles available as a download format

MP4
MOV
MKV
AVI
WEBM
WMV
FLV
M4V

About this tool

There's no need to extract the audio beforehand. Upload the MP4, MOV or MKV directly: we split the sound track off ourselves, without re-encoding the video or storing it anywhere else.

Converting two hours of recording to MP3 before uploading costs time and, usually, some quality. With this tool that step isn't necessary.

Features

We extract the audio automatically: nothing to convert on your side.
Timestamps are synchronised with the video.
Voice identification, essential for transcribing interviews clearly.
Export to SRT and VTT, compatible with editors and HTML5 players.

How it works

1
Upload the video
Any usual container, up to 50 GB. Only the audio track is processed.
2
We transcribe the audio
With voices identified separately and a timestamp on every line.
3
Download the text or the subtitles
DOCX and PDF for reading; SRT and VTT to add to the video.

Use cases

Classes and training

The text works as notes, a searchable index and an accessible version.

Recorded video calls

Zoom, Meet and Teams generate MP4 files. Upload them directly.

Social media video

Generate subtitles in the same operation, essential for sound-off viewing.

In detail

Of the whole video, only the audio is used

There's no need to convert anything beforehand. The file is uploaded as is, the internal audio track is processed, and the picture is never analysed: it adds nothing useful to the transcription and would only slow the process down.

This applies to all common containers: the MP4 from a phone, the MOV from an iPhone, the MKV from a screen recording, the WEBM from a downloaded meeting. If the file contains audio, it's transcribed; if it doesn't, you're told before any minutes are used from your quota.

The difference between a transcript and subtitles

A transcript is continuous text meant for reading: paragraphs, speaker identification and, optionally, a summary. Subtitles are that same content split into two-line blocks that stay on screen just long enough to read, each with its own start and end time.

This tool produces the former; the latter can be downloaded from the same screen as SRT or VTT without repeating the process. It's worth deciding in advance which one you need: a transcript for an article or notes, subtitles to add to the video.

Frequently asked questions

Need to transcribe a video?

Upload it and get the text with timestamps, each voice identified and a summary. No account needed to start.

Transcribe my recording See pricing