Difference between revisions of "+AI Transcription"

Latest revision as of 11:37, 26 March 2024

Overview

This article is about using AI to generate English transcriptions for uploaded media files. The transcription can be generated by the AI in either text or subtitle format. Users who prefer not to watch the entire media file can conveniently examine the generated text file. Additionally, a text file could be leveraged with other AI capabilities. For example, users could request the AI to generate a paragraph summary based on the text transcript. In this article, you will learn how to configure and manage AI-generated transcripts. You will also learn how to store transcription data in a custom field for later additional processing.

Note: The +AI Transcription feature supports 98 input languages and the output is always an English transcription file. Only the following media file types are supported for transcription: MP3, MP4, MPEG, MPGA, M4A, WAV, and WEBM. You will need an OpenAI license to use AI features on SmartSimple. You must be a Global Administrator to enable this feature. Contact your account manager or sales@smartsimple.com for further information on billing and implementation.

For a general overview of the +AI Transcription feature, watch this video.

To watch this video in full screen, please click on the full screen button on the bottom right.

Configuration

Setting up +AI Transcription

Follow these steps:

1. Create a new custom field with the Field Type set to “Text Box - Multiple Lines”. Under Caption, enter “AI Media Transcript”.
2. (Optional) Toggle on Label as AI-Generated Content.
3. Click Save.
4. Create or edit an existing upload custom field. Under the File section, toggle on Enable +AI Transcription.
5. Under +AI Transcription Format, select the “Text” option if you want a basic transcript of the media file. Select “Subtitle” if you want the timestamps along with the transcription.
6. Select the text box custom field we created in Step 1 for the To Custom Field dropdown located under the Value Storage section.

Triggering +AI Transcription

Once +AI Transcription has been set up in the previous section, we can access the transcription contents by following these steps:

1. Go to the desired UTA record and upload a media file such as a video interview or application.
2. Save the record. When the page reloads, the text box custom field we created ( “AI Media Transcription”) will be populated with an English transcription of the uploaded media file.

With access to the contents of this custom field, you can continue to maximize AI capabilities by translating the transcription, asking the AI to summarize the contents of a transcription, or even query the AI about the contents of the transcript to aid in the review process.