This article is an overview of the AVI feature. Audio/Video Intelligence offers advanced capabilities for extracting insights from video and audio content, such as detecting faces, recognizing speech, and generating transcripts.

What is Audio and Video Intelligence?

With Audio/Video Intelligence, users can significantly reduce the time they spend manually tagging video and audio assets as well as, searching these assets for specific events, people and time stamps.

The feature automatically tags and transcribes audio and video assets, improving asset discoverability and helps users to identify elements and scenes within their library content. Ultimately, it empowers users to get more value out of their video content by speeding up content management, searchability, and their ability to source content for further content creation.

What formats are compatible?

AVI can be run on the following file types:

  • Audio Files - WAV, MP3, WMA, FLAC, OGG
  • Video Files - MP4, M4V, AVI, MOV, MPG, MPEG, ASF, FLV, MXF, TS, M2T, WMV, MKV

What languages are detected/supported?

Audio/Video Intelligence (AVI) can transcribe assets after automatically detecting the following languages:

Single language files

  • English
  • Spanish
  • French
  • German
  • Italian
  • Mandarin Chinese
  • Japanese
  • Russian 
  • Portuguese (Brazilian) 

Multi-language files

  • English
  • French
  • German 
  • Spanish 

com009.svgNote: Even though the video indexer supports Arabic (Modern Standard and Levantine), Hindi, and Korean, these languages are not supported in automatic language detection. 

Translating the transcript 

The transcript can be translated and downloaded in 57 supported languages:

Afrikaans, Arabic, Arabic (Syrian Arab Republic), Bangla, Bosnian, Bulgarian, Catalan, Chinese (Cantonese, Traditional), Chinese (Mandarin, Simplified), Croatian, Czech, Danish, Dutch, English, English (Australia), English (United Kingdom), Estonian, Fijian, Filipino, Finnish, French, German, Greek, Haitian, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Kiswahili, Korean, Latvian, Lithuanian, Malagasy, Malay, Maltese, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Samoan, Serbian (Cyrillic), Serbian (Latin), Slovak, Slovenian, Spanish, Swedish, Tamil, Thai, Tongan, Turkish, Ukrainian, Urdu, Vietnamese

What permissions do I need to use Audio/Video Intelligence (AVI)?

The following permissions are applied for Audio/Video Intelligence by default.

  • Administrators & Library Administrators: View, Edit & Index 
  • User Administrators, Contributors, Approvers, Members, Guests: View

Users who are not in those groups can have video intelligence permissions enabled through custom permissions. 


Running AVI on your Video Assets

How do I get started with running AVI on an asset?

  1. Select the asset you would like to run AVI by clicking on the Detailed Information icon. 
  2. Click on the Run Video Intelligence button. Your video asset will begin processing. 

2024-03-18 23_21_12-MediaValet.png

com009.svgNote: On average, processing takes about as long as the length of the video itself (e.g. a 5 minute video will take 5 minutes to process)

How can I run Audio/Video Intelligence (AVI) on multiple assets?

  1. To run AVI on multiple assets at once, select your video assets and click the Actions menu.
  2. Select Run Audio/Video Intelligence. We recommend running AVI on no more than 50 video assets at a time.

2024-03-18 23_09_16-MediaValet.png

com009.svgNote: We recommend running AVI on no more than 50 video assets at a time.


Working with AVI Features

Can I modify the Audio/Video Intelligence (AVI) transcript and information?

You can edit the transcript by selecting the pen icon in the top right-hand corner and select Timeline. You can also edit the speaker's name and the time frame.

2024-03-18 23_42_44-Settings.png

Alternatively, you can download the transcript in several file formats.

2024-03-18 23_36_50-MediaValet.png

In the Insight tab, you will be able to edit the people's name, view the topic of the video, the detected keywords and labels.


Is the Insights view customizable?

Yes, you can chose to display or hide a variety of information by clicking on the layers icon.

2024-03-18 23_38_04-MediaValet.png


How can you search for assets with Audio Video Intelligence (AVI)?

Within the Filters tab in your MediaValet home screen, you can filter by file type and narrow down your search results to Videos or Audio Files with Audio/Video Intelligence (AVI) or without Audio/Video Intelligence (AVI). Find the videos/audios you still have to index, or find the ones that you have already indexed.

2024-03-18 23_33_01-MediaValet.png

Was this article helpful?
0 out of 0 found this helpful