Video to text,
transcribed in minutes.
Drop an MP4 or any video and get a clean transcript back in readable paragraphs. Copy it, add timestamps, or download it as TXT, SRT or VTT. The first 5 minutes are free.
The first 5 minutes of transcription are free, no card. Your video comes back with you after signing in. Copying the text and downloading TXT, SRT or VTT is always free. Pro is $5/month for 100 minutes.
How to transcribe a video to text
- Pick the video. Choose an MP4, MOV, WebM, MKV or an audio file up to 5 GB. The audio track is extracted in your browser, so the video itself is not uploaded.
- Transcribe. Whisper turns the speech into text with a timestamp for every word, in the language that is spoken.
- Read and tidy. The transcript comes back in paragraphs split at pauses and sentence ends. Switch timestamps on to see where each paragraph starts.
- Copy or download. Copy the text in one click, or download it as .txt, or as .srt and .vtt subtitle files with timing.
Behind the button, the audio track is copied out of the video inside your browser, so a 2 GB screen recording becomes a few megabytes before anything leaves your device. Whisper transcribes that audio with a timestamp for every word, and the tool groups the words into paragraphs: a new one starts where the speaker pauses after a sentence, or once a paragraph gets long.
Transcribe TikTok, Instagram, Facebook and Zoom videos
The transcriber works on files, so for a video that lives on a platform you first get the file, then pick it here.
- TikTok: tap Share, then Save video, and pick the saved MP4. For a public TikTok the TikTok transcript tool takes the link directly.
- Instagram Reels: where Instagram offers it, Download in a Reel's share menu saves the MP4; your own posts are also in Download your information in the Accounts Center. Otherwise a screen recording with sound works.
- Facebook: download your own videos from the video's menu, or from Download your information in the Accounts Center.
- Zoom, Google Meet and Teams: cloud recordings download as MP4 (or M4A audio only, which is quicker to pick). Local Zoom recordings sit in the Zoom folder in Documents.
- YouTube: when the video already has captions, the YouTube transcript tool copies them without spending any minutes.
Only transcribe recordings you made or have permission to use.
Transcript or subtitles?
A transcript is text for reading: show notes, a blog post, quotes, meeting minutes, or a prompt for an AI summary. Subtitles are the same words cut into short timed cues for showing on the video. This page gives you both: copy the text, or download the .srt or .vtt. To tune the cue length for YouTube or Shorts, use the SRT generator; to fix lines in a subtitle file, use the SRT editor; and to change format, the SRT to VTT converter.
Want the words on the video itself, the way TikTok and Reels captions look? Open the transcript in the editor, pick a caption style and export an MP4 with the captions burned in, or bring a finished file to add SRT to video.
Add subtitles to your video for just $5/month.
100 minutes of AI transcription, viral caption styles, burned-in MP4 export. No watermark. Cancel any time.
5 minutes free · No credit card · Cancel any time
Frequently asked
How do I convert an MP4 to text?+
Pick the MP4 above and press Transcribe to text. The audio is copied out of the video in your browser, Whisper transcribes it, and the transcript appears in paragraphs. Copy it or download it as a .txt file.
Can I transcribe a video for free?+
Yes. The first 5 minutes of transcription are free after a free sign-up, no card. Copying the text and downloading TXT, SRT or VTT never costs anything. For more, Pro is $5/month for 100 minutes of transcription a month, plus 100 minutes of MP4 export with burned-in captions.
How accurate is the transcript?+
The tool uses Whisper large, one of the most accurate speech models available. On clear speech most words come out right with punctuation; names, brands, jargon and heavy crosstalk still need a read-through. Background music and a distant microphone lower accuracy more than accents do.
Which languages can it transcribe?+
Whisper detects the spoken language by itself and writes the transcript in that language, across 99 languages including Spanish, Portuguese, French, German, Hindi, Japanese and Arabic. It transcribes; it does not translate.
Which file types and sizes work?+
MP4, MOV, M4V, WebM, MKV and AVI video, and MP3, M4A, WAV, AAC and OGG audio, up to 5 GB per file. Long recordings are cut into 10-minute parts that are transcribed in parallel and stitched back together, so an hour-long meeting comes back as one transcript.
Is my video uploaded or stored?+
The video stays on your device: only the extracted audio, a few megabytes, is sent for transcription, and it is deleted as soon as the transcript comes back. The transcript is built in your browser and is not saved on our servers. Videos you upload to the caption editor for export are deleted after 2 days.
Can I get the transcript with timestamps?+
Yes. Turn on Timestamps and each paragraph starts with the time it is spoken, like [2:15]; the copy and .txt download include them. For a timestamp on every line, download the .srt or .vtt instead.
How do I transcribe a TikTok or Instagram video?+
Save the video to your phone or computer first (TikTok's Save video, or a screen recording for Instagram), then pick the file here. For a public TikTok you can also paste its link into the TikTok transcript tool.