Skip to main content
Version: V12

Multi-Language Audio Transcription with On-Demand Processing Using AWS Indexer

Multilanguage Audio Transcription empowers users to transcribe audio in various languages, streamlining and enhancing the transcription process. Users will gain enhanced control and flexibility in selecting language preferences for transcription tasks, leading to accurate and tailored results. Additionally, automated language detection functionality within media files ensures precise transcription accuracy, particularly in scenarios involving language switching among speakers during conversations or when multiple participants utilize different languages.

To learn more, see Multi-Language Audio Transcription in VIDIZMO.

Prerequisites​

  • Verify that the Transcription feature permission is enabled for your group. This allows you to generate transcripts within your portal.
  • Confirm that your subscription package includes the redaction feature.
  • Verify that the AWS Video Indexer is properly configured and enabled in your VIDIZMO Portal.
  • Ensure that the Storage Provider in VIDIZMO is configured to use AWS for storage.

Automatic Processing​

To automatically generate multi-language audio transcriptions for your media files upon upload to the portal, enable automatic processing in the AWS indexer. Once a media file is uploaded, the system will initiate processing to generate the transcript.

For detailed instructions, see How to Configure AWS Indexer App.

On-Demand Processing​

  1. In the media library, select the overflow menu (three dots) on the media file you want to process.
  2. Select Process.
  3. Select Generate AI Insights to access the available options.
  4. In the Transcription Language Mode section, select Specific Language to manually choose the language you are sure of, Auto Detect to allow the system to determine the main language spoken, or Auto Detect Multiple Languages if your media file includes several languages.
  5. Select the language(s) for improved transcription accuracy. You can manually choose at least two dominant languages or leave it empty if unsure. In Specific Language mode, only one language can be selected.
  6. In the Insights field, select Transcriptions to enable transcription generation.
  7. Select Start to initiate the processing.

Once processing is complete, the transcription appears in the transcription pane on the playback page.

See Also​

Did you find this article helpful?