Skip to main content
Version: V12

Configuring VIDIZMO Indexer for Transcriptions

The VIDIZMO Indexer generates transcriptions for your audio and video files. It automatically detects the spoken language in your content to generate the transcription.

Prerequisites​

  • Ensure you belong to a group where App Management and Transcription and Speaker Diarization features are enabled.
  1. In VIDIZMO, select the menu icon in the top-left corner to open the navigation pane.
  2. Expand the Admin section and select Portal Settings.
  3. Go to Apps > Content Processing.
  4. Select the settings icon on the VIDIZMO Indexer app.

Configure Transcription​

  1. Media Formats Select the media format(s) you want to generate transcriptions for. Transcription is available for Audio and Video formats. The available insight options depend on the selected format(s). In a DEMS Portal, this field appears as Evidence Formats.

  2. Insights From the dropdown, select Transcription/CC to generate transcriptions and closed captions for your audio and video content. You can also add other AI insights in this field to apply them alongside transcription.

  3. Transcription Language(s) Select how languages are detected for transcription. Auto-detect is selected by default, which automatically detects the spoken language in your content.

    For the list of supported languages, see How to Generate Transcriptions using VIDIZMO Indexer.

  4. Automatic Processing Select On to automatically process uploaded content for transcription, or Off to require on-demand processing.

  5. Select Save Changes to apply your settings.

  6. Turn on the toggle for the VIDIZMO Indexer app to enable processing.

Did you find this article helpful?