Use Alteryx to Turn Video Captions Into Readable Text!

[BenoitC]

Transcription is now a great feature of Microsoft Stream. When uploading any videos to the Office 365 streaming service, Microsoft can automatically add captions. Once uploaded, you can download transcriptions.

Captions are great but not if you want to use it in a readable format:

Before Alteryx...

After Alteryx...

Alteryx is there to back you up! 😎  After extracting the VTT file, you can upload them to this simple workflow to have your text ready:

First, you need to download the captions file generated by your video upload. Then get rid of all the time stamps you can see in the above image. You can copy and paste the content of the caption file directly into the Alteryx canvas. This will automatically generate a Text Input tool.

Next, keep only the text lines. This is easily done by using two sample tools: one to skip the first rows and the second to gather all the lines of text.

Then, concatenate all lines into a single paragraph. One of the cool features of the Summarize tool is the ability to merge multiple lines of text into a single paragraph.

Finally, add the Table and Render tools to output the text into a Word document!

Follow these steps anytime you need the transcript of a video in a usable format! A meeting recording with a ton of technical terms? Want to quickly paste the transcript into an email? You name it!

To sum up, here are the 4 easy steps to follow:

1) Upload a video in Microsoft Stream, captions are automatically activated.

2) Download and copy/paste text from the VTT file (use notepad to open it) directly in the workflow, it will generate a Text Input tool.

3) Add Sample and Summarize tools, click run. Your transcript is readable!

4) Add reporting tools for the Word doc.

Enjoy !