Video to Transcript — Timestamped Text, SRT & DOCX

Upload a video or audio file. Get the full transcript as text.

Upload a video or audio file and get an editable transcript with timestamps. Export TXT, DOCX, PDF, SRT, VTT, JSON or CSV.

Drop your recording here

Choose video

Upload Video to Transcribe

Free: up to 30 min · Pro: up to 4 h

Transcript excerptSample from a short interview. Not your file.
00:01:12

Maya Chen: We shipped the cut on Thursday.

00:01:18

Jordan Hale: The captions still overlap on the second line.

Supports MP4, MOV, MKV, WebM, MP3, WAV, M4A and 8 more formats.

Free: up to 30 minutes per file · 2 GB maximum.

Batch upload, process many videos in one go, is on Pro.

How to convert a video to a transcript

4 steps
  1. 1. Upload your video

    MP4, MOV, MKV, WebM, MP3, WAV and 14 more formats. Free: files up to 30 minutes and 2 GB. Pro: up to 4 hours and 10 GB.

  2. 2. Choose language and options

    Auto-detect or pick the spoken language. Add names and terms, speaker labels (Pro) or a translation.

  3. 3. Review the transcript

    Search it, play any line from its timestamp, and switch timestamp mode: per interval, per segment, per speaker or none.

  4. 4. Export

    TXT, DOCX, PDF, SRT, VTT, 3-column PDF or DOCX, JSON, CSV or Notion.

What you get from one upload

6 capabilities
  • Timestamps your way

    Per interval (30 s by default), per segment, per speaker or none, plus calculated SMPTE timecode at common frame rates.

  • Speaker labels (Pro)

    Speaker turns are labelled only when the audio has them. Nothing is invented.

  • Long recordings

    Pro handles files up to 4 hours each, and batches of up to 20 files at once.

  • Edit before export

    Correct text inline on Pro. Exports always include your latest edits.

  • Every delivery format

    Documents, subtitle files and data exports from the same transcript.

  • Verbatim mode

    Full verbatim or clean verbatim, chosen before you export.

Real example

Real before and after. 1 example
A 44-second video turned into a timestamped transcript
Frame from a 44-second NASA science video before transcriptionBefore
Timestamped transcript exported as TXT from the same video, with markers every 30 secondsAfter, VideoText output

VideoText transcribed this 44-second clip and exported the text with a timestamp every 30 seconds. The same transcript can also be exported as SRT, VTT, DOCX, PDF, JSON or CSV. The transcript is shown exactly as exported, including one speech-recognition repeat at “lab testing. a laboratory study”, which you can correct in the editor.

Source clip: NASA ScienceCasts, public domain. NASA does not endorse VideoText.

Real output · 44-second clip → TXT

Input
nasa-asteroid-sample.mp4 · 44 s · English (auto-detected)
Output (excerpt)
[0:00]
Following launch in 2016, the OSIRIS-REx spacecraft will travel to near-Earth asteroid Bennu, study it from orbit, and ultimately bring back a sample for lab testing. a laboratory study on Earth. Near-Earth asteroid Bennu interests researchers for two reasons. First, it is a carbon-rich asteroid that could harbor amino ac…

Exactly as exported, including one recognition repeat you can correct in the editor.

Who uses Video to Transcript

Research interviews, Podcast and video production, Client transcript delivery
  • Research interviews

    Timestamped transcripts you can cite and search, exported to DOCX or CSV.

  • Podcast and video production

    Show notes, quotes and an SRT for the edit from one upload.

  • Client transcript delivery

    Transcribe, then fix and format the transcript to a client style guide.

  • Meetings and lectures

    Long recordings on Pro, with chapters and a summary where available.

Frequently asked questions

9 questions

How do I convert a video to a transcript?

Upload the video, choose the spoken language (or leave auto-detect) and generate. When it finishes, review the text and download TXT, DOCX, PDF, SRT or VTT.

Can I get a transcript with timestamps?

Yes. Choose per interval (every 30 seconds by default), per segment or per speaker, or turn timestamps off. Calculated SMPTE timecode is also available.

Does it label different speakers?

Speaker labels are a Pro feature. They appear only when the recording actually has more than one speaker.

Can I transcribe a video to text for free, and how long can it be?

Free handles files up to 30 minutes and 2 GB. Pro handles up to 4 hours and 10 GB per file.

Can I transcribe multiple videos at once?

Yes on Pro: batch up to 20 files and download the finished transcripts together.

Which formats can I upload and export?

Upload MP4, MOV, MKV, AVI, WebM and common audio files such as MP3, WAV, M4A and FLAC. Export TXT, DOCX, PDF, SRT, VTT, 3-column PDF or DOCX, JSON, CSV or Notion.

Can I edit the transcript before downloading?

Yes on Pro. Edits are saved and included in every export.

Can I translate the transcript?

Yes, with a free account. Choose a language before you start, or paste a transcript into Translate an existing transcript. Translated exports appear only once the translation has finished.

Is there a watermark on free exports?

Free text exports include short VideoText watermark notes. Pro exports are clean.

Next steps for your transcript

Turn your next recording into a transcript

Timestamps, speaker labels and every export format from one upload.

Upload Video to Transcribe