If first time using the tool go ahead and setup the STT API system first.

1. Adding a video/audio

  1. Click on new
  2. Chose the media you want to open, audio or video.
  3. Fill in title and description
  4. Chose Speech To Text system you want to use (IBM American English is the default)
  5. Save Transcription

Getting started adding media

For a list of supported media file type see ffmpeg(which is what has been used for the file conversion under the hood)

The transcription will take a round 5 minutes to process regardless of the length of the media.

processing transcription

2. Selecting text from a transcription

Make selections of text you’d like to include in your video sequence.


3. Exporting a video sequence(EDL)

Export an EDL, which is an Edit decision list.


You can export a video sequence of selection as they appear chronologically in the video. Or you can export them in the order you selected them, getting you closer to make a paper edit.

4. Reconnect in video editing software of choice

EDL is compatible with all major editing software.

  • Adobe Premiere
  • Avid Media Composer
  • Final Cut Pro 7
  • And any other editing software that lets you import an EDL file…

To import the EDL and reconnect the sequence

  1. Import the EDL
  2. Go to the sequence
  3. Reconnect the offline sequence
  4. Continue your editing

Adobe Premiere example

processing transcription

a Note on working with Final cut pro X
For now a workaround for Final cut pro X not supporting EDL is that you can open the EDL in Davinci resolve convert it to XML that will work with final cut X.