OpenSEP
Use case

Turn a lecture recording into text you can search.

To turn a lecture recording into text, upload it to OpenSEP. You get a transcript with a timestamp on every line, so a passage is easy to find again, and speakers are detected automatically with no speaker count to enter. Export it as SRT, VTT or JSON. The Free plan takes files up to 5 minutes; Pro up to 2 hours.

What goes in

  • A recorded lecture, talk or seminar.
  • An audio file: MP3, WAV, FLAC, M4A or OGG, or an MP4 video of the lecture.
  • Only a recording you have the speaker's permission to process.

What comes out

  • A transcript in the spoken language, with a speaker label and a timestamp on every line.
  • Speakers that cannot be told apart may share one label.
  • Questions from the audience that the microphone barely picked up may be missed. Check them against the recording.
  • You choose the spoken language, or let it be detected. The transcript is not translated.
  • An export as SRT or VTT subtitles, or as JSON for your own tools.

Get the transcript

  1. Upload the lecture recording.
  2. Choose the spoken language, or leave it on automatic detection.
  3. When the job finishes, read the transcript and use the timestamps to jump back to a passage.
  4. Check names and technical terms against the recording.
  5. Export SRT, VTT or JSON. Results are deleted 3 days after they are produced.

File limits

  • Free: files up to 5 minutes and 128 MiB
  • Standard: files up to 30 minutes and 768 MiB
  • Pro: files up to 2 hours and 3 GiB

Compare every plan

A few useful answers

Before you begin.

More questions? Visit the help center

My lecture is longer than my plan allows. What can I do?

The Free plan takes files up to 5 minutes and 128 MiB, Standard up to 30 minutes and Pro up to 2 hours. A longer lecture needs a higher plan, or split it into parts and transcribe each one.

Will the audience's questions be in the transcript?

Questions picked up clearly by the microphone are transcribed. Faint ones far from it may be missed, and speakers that cannot be told apart may share one label.

Should I check technical terms?

Yes. Names, terms of art and formulas read aloud can be transcribed wrongly. Check the passages you will quote against the recording.

Try it on your own file.Open your workspace