Free online tool · No account

Convert video to text

Drop in a talking clip and get the transcript for free as TXT, DOCX, PDF or SRT. Cliptag also names your video to match what is in it, online and without signing up.

Drop your file here

or pick a file from your computer

Choose file

One file, up to 10 minutes / max. 1 GB

Transcript as TXT, DOCX, PDF or SRTTimecodes for subtitlesLanguage detected automatically

Timecodes included

The transcript comes back split into segments with start and end times, which is what an SRT file is made of. Drop that next to your video in any editing program or upload it with the video, and the subtitles sit where they belong. TXT gives you flowing text for reading and searching, DOCX and PDF are for handing it to someone else.

1
00:00:00,000 → 00:00:03,400
Today we are standing right in front of the Great Pyramid.
2
00:00:03,400 → 00:00:07,900
In a moment we show you the view from above.
TXT DOCX PDF SRT

The language is detected automatically

You do not have to set anything. The model recognizes the spoken language on its own and transcribes in it, which covers the usual editing languages and a good many more. Speech recognition works on what it can hear, so a clean recording with little wind and background noise gives a noticeably better transcript than a windy one.

DeutschEnglishFrançaisEspañolPortuguêsItalianoNederlandsPolskiSvenska日本語한국어中文 …

For a whole shooting day

This page takes one clip up to ten minutes. Cliptag on your Mac transcribes every talking clip in a folder, saves the transcript next to the video, and lets you cut in the text: delete filler words, long pauses and false starts, and Cliptag renders a rough cut next to the original. There is also a local mode that transcribes on your Mac without any internet at all.

In the app: the whole card

▾ Day-1_2026-08-04
▾ 01_Giza-Plateau
Pyramids-of-Giza_16x9_4K_60FPS_DJI.MP4
Camel-Ride-at-Sunset_16x9_4K_60FPS_DJI.MP4
▾ 02_Hotel-Room
Intro-to-the-Trip_9x16_4K_30FPS_IPHONE.MP4
Talking clip Scene clip
App only

Name a person once, find every shot

Cliptag finds faces in photos and clips and groups matching people. You give a person a name once, and it sits as a Finder tag on every match. The matching runs entirely on your Mac, without the cloud, and works in local mode too.

Download free for Mac
Lena
Pyramids-of-Giza_16x9_4K_60FPS_DJI.MP4 Lena
Camel-Ride-at-Sunset_16x9_4K_60FPS_DJI.MP4 Lena
Intro-to-the-Trip_9x16_4K_30FPS_IPHONE.MP4 Lena
FAQ
Is my video uploaded?

No, not in the normal case. Your browser decodes the audio track and only the audio is sent for transcription. The video file stays on your computer. Only for a few formats that browsers cannot read at all do we need the file itself, and the page says so before it starts.

Which languages are supported?

The spoken language is detected automatically and transcribed in that language. The common editing languages are covered, and many beyond them.

Do I get timestamps and subtitles?

Yes. The transcript is segmented with start and end times, and the SRT export uses them directly, so it works as a subtitle file in any editing program.

How long may the clip be?

Up to ten minutes on this page. That is a limit of the demo, not of the product; the Mac app has no length limit.

Does this cost anything, or need an account?

No. The online tools are free and there is nothing to sign up for.

Generate video titles AI sets title and tags to match the video Rename and transcribe Both results from one clip