Konthora

Konthora converts video files into text transcripts for free in the browser. MP4, WebM, and MOV are accepted, the audio track is extracted automatically, and you can export the result as TXT, SRT, VTT, or JSON with sentence, paragraph, or word-level timestamps. Uploads are up to 100 megabytes and 10 minutes long, and are deleted after 60 minutes.

Video Transcription

Video to Text with Automatic Audio Extraction

Upload an MP4, WebM or MOV file. Konthora extracts the audio track, transcribes the speech in it, and gives you timed subtitles you can upload anywhere.

Upload media

Audio and video transcription

Up to 100 MB
Drag & drop your file here, or click to browseSupported formats: .MP3, .WAV, .M4A, .AAC, .MP4, .WEBM, .MOV
Maximum file size: 100 MB

Currently supports English-language audio only.

Export Format
Ready to transcribeChoose a file, timestamp grouping, and export format.
Your files are processed securely and automatically deleted after 60 minutes. Privacy

Transcription Output

No transcription results yet

Upload an audio or video file and click Transcribe Audio. Your timestamped transcript and export controls will appear here.

Video-specific

How Konthora handles video files

It transcribes the audio track, not the picture. That distinction decides what you get back and when this tool is the wrong choice.

MP4, WebM, MOV

The formats most cameras, phones and editors actually produce.

Audio track extraction

The track is extracted and prepared automatically. No separate audio file needed.

Subtitle-ready timing

Word-level timestamps keep captions in sync instead of trailing the speaker.

Spoken audio only

A silent or music-only video produces no text, because there is no speech to read.

How it works

Get subtitles from a video in three steps

Upload a clip and receive timed captions plus a readable transcript.

1

Upload the video file

MP4, WebM or MOV, up to 100 MB and 10 minutes. Longer clips need splitting first.

2

Choose word-level timing for captions

Word timestamps keep each cue in sync with the speaker. Use sentence level for a readable transcript instead.

3

Export SRT or VTT

SRT for most platforms, VTT for HTML5 players. Keep the file after uploading so you control the timing.

Who it is for

What people transcribe video for

Captions, searchable archives, and accessibility for published video.

Captions for published video

Upload your own SRT or VTT rather than relying on a platform auto-caption.

Searchable video archives

Make a back catalogue findable by what was actually said in it.

Accessibility

Captions make video usable for viewers who cannot rely on the audio track.

Chapter and highlight discovery

Punctuation at the sentence level lets you jump to the part that matters.

Video to Text FAQs

Common questions about transcribing video files.

Which video formats can I upload?
MP4, WebM and MOV. Konthora extracts the audio track automatically, so you do not need to produce an audio file first. Upload the original where you can, since re-encoding introduces artefacts the model hears as garbled speech.
What happens to the visuals in my video?
They are not transcribed. Konthora reads the audio track, so on-screen text, slides and footage carry no text of their own. If your video has no narration the transcript will be empty.
Which timestamp mode should I use for subtitles?
Word level. It times each word individually, so a caption reflects what is being said at that moment instead of holding a whole sentence while the speaker has moved on. That tracking is the difference between usable captions and frustrating ones.
Can I make captions for a YouTube video?
Yes. Export SRT and upload it, then keep your copy. Platforms generate their own captions, and yours will be indexed on your own domain rather than only inside the platform.
How long can a video be?
100 MB and 10 minutes per file. Split longer videos at scene changes and overlap the joins by about a second so no sentence is lost at the seam.
What happens to my video after I transcribe it?
The upload and the resulting transcript are deleted automatically after 60 minutes, so export the caption file before that window closes rather than planning to come back for it.
My video already has burned-in captions. Will they be transcribed?
No. Burned-in text is part of the picture rather than the audio, so it is not speech and is not read. Upload the original audio track if you need those captions extracted.