Auto-generated Transcripts and Captions

Computers are getting better at auto-generating transcripts and captions and can be a valuable part of the production process, especially when combined with manual review. Here are some products that can help:

Microsoft Stream

As part of Office365, there is a video hosting platform called Stream. If you upload a video, Stream will use AI to automatically generate captions. The quality is surprisingly good. It also has an editor which allows you to edit the captions. Once you are done, you can download the captions, as a WebVTT file, and then use it for whatever platform you like.

You can access Stream by logging into your university Office 365 account. You will see list of apps. If you click on ‘All apps’, you should be able to open Stream. Upload your video. It then auto-captions it and you can edit the results. By default, your uploads are set to private.

But you can easily convert WebVTT to SRT using an online converter.

If you prefer another format, you can convert WebVTT to TXT, Word or PDF.

Cost: Free


Trint is a transcription services which allows users upload audio or video, transcribe it and correct errors. The transcript can then be exported in various formats, including MS Word, SRT and VTT.

Cost: $0.22 USD per minute

You-tube Captions

Everybody has probably seen You-tube's audo-captions in operation. You-tube allows you to edit auto-captions and then download them. Google will index the edited captions, thereby making your video easier to find by searching.

Cost: Free

IBM Watson

IBM also offers automatic generation of captions using its Watson Speech to Text technology.

Cost: $0.02 USD per minute

Other Tools

Sometimes you want to convert timed text files, such as SRT or VTT, into transcripts (TXT). There are several free online tools that will do this for you.

Contact Us

For assistance or to report accessibility problems please contact:

Andrew Normand
Web Accessibility Lead
Phone: +61 3 9035 4867