Using real-time transcription
This section is part of the AI Live Streaming Manual. It explains how event organizers can make the AI text conversion and translation(s) available in the form of a real-time scrolling transcript without delay for on-site participants (or remote participants in virtual events).
Delivery
Since participants need to get the stream without delay, WebRTC is used instead of HTTP Live Streaming (HLS) for delivering the real-time transcript. This is supported by all modern (mobile) browsers. By default, the AI Multilingual plan allows for 5 simultaneous real-time transcription viewers, but you can contact us to add more viewers to your plan.
The look and feel of the scrolling transcript can be customized by the user, via the cog wheel in the top-right corner of the transcript page.
Configuration
Follow the normal workflow to create an event with AI captions.
In the AI wizard, make sure to check 'Provide real-time transcription for event attendees'.
You can change this option on the 'Caption Languages' tab of the Event page. If it is set to 'Yes', a 'Real-time Transcription' panel appears on the bottom of the page, which contains the links to page(s) with the real-time transcript for each caption language. Distribute the transcript links to your on-site production team and/or event participants.
There are 2 kinds of transcription links:
- On-site participant links: intended for distribution to event participants, so they can read the transcription on mobile devices. The scrolling text is only displayed when the event status is
Started
. - On-site production links: intended for the event organizer to display the scrolling text on-site, for example on large screens. The scrolling text is also displayed when the event status is
Preview
orPaused
.
Notes:
- Clevercast lets you combine a live stream with closed captions (using HLS, with a delay for increased accuracy) with a transcript for event participant (using WebRTC, without any delay). Please note that enabling 'Real-time Transcription' may, to a limited extent, negatively affect the quality of the closed captions in the live stream. So if you don't have on-site users, we recommend leaving this setting turned off.
- Since transcription has to be done in real-time, the accuracy of translations in transcript form will be slightly lower than the accuracy of translated closed captions in the live stream (where the delay allows Clevercast to send more context to the AI models). Note that automatic adjustments, based on the event's AI Vocabulary, do get applied to real-time transcripts. In contrast, adjustments by human correctors do not (they only affect captions and audio in the video player).
Follow the normal workflow to test, start and stop your live stream, including the real-time transcription.