Enabling Better Engagement and Accessibility with New Session Transcriptions and Live Captions

We’re delighted to announce two new Beta AI-powered features for Whereby Embedded customers that enable higher engagement and presence in video calls, increased accessibility within the meeting room, and vital post-call documentation.

4 mins read | Thu 13 March 2025

Our vision is to create a world in which anywhere works; by making video call experiences more efficient and accessible we hope to enable more people to create valuable connections via video.

We’re delighted to today announce two new Beta AI-powered features for Whereby Embedded customers that enable higher engagement and presence in video calls, increased accessibility within the meeting room and vital post-call documentation.

Whether a consultation with a doctor, or a virtual classroom, we’re confident that our new Session Transcription and Live Caption features will significantly improve the video call experience for our customers and their end users.

Both features are now available in Public Beta to all customers on paid Whereby Embedded subscriptions.

Session Transcriptions

Virtual conversations can pose challenges in building a rapport and a trusted relationship. Particularly in clinical settings, these personal connections are the foundation of trust building which is frequently a barrier to telehealth engagement. We believe that by empowering hosts with features that remove distractions and allow them to maintain focus on the conversation, trust can be established and human connection restored. It can also help to reduce tech fatigue by reducing manual tasks from workloads.

While Whereby is (and always will be) focused on building world-class WebRTC video calls, we also see huge potential in AI-powered features as enhancers to virtual communication.

The release of our new Session Transcriptions into Public Beta offers a plug-and-play option for users of the Whereby Embedded API to produce transcripts directly from live sessions.

Session Transcriptions allows you to produce a transcript directly from the live session, without the need to record it. Transcripts of the video call are available as soon as the session ends either by downloading them from your Embedded dashboard or programatically via the API.

The transcriptions can then be referred to later or further analysed and summarized outside of our systems.

How do I set it up?

You can enable and configure Session Transcription globally for your account, or individually for each room depending on your needs. They can either be configured from your Whereby Embedded dashboard or via the API.

Read the developer documentation.

How do I access the transcriptions?

Transcriptions can be set up either to be stored in Whereby-hosted storage or sent to your Amazon S3 bucket.

All transcripts can be downloaded manually through the dashboard, or programmatically through API requests.

Live Captions

We know that accessibility is more than just a checkbox for our customers. It is vital, particularly in healthcare and education settings that all users, whatever their needs, technical literacy or location can engage in video calls.

We are delighted to now provide Live Captions in Public Beta within Whereby Embedded meeting rooms. When enabled, participants can see captions visible within the meeting room UI in real-time.

How do I set it up?

Live Captions can either be enabled globally for your entire Embedded account via the dashboard, or configured on a per-room basis via the API.

Live Captions can either be used independently or in tandem with Session Transcriptions to keep a record of the conversation once the meeting has ended.

Read the developer documentation.

How much do these new features cost?

Both of these new features are available on Build and Grow plans and are supplementary to your Whereby Embedded plan, incurring an additional charge based on usage.

Both Session Transcriptions and Live Captions are charged at $0.024 per unmuted participant minute.

What is an “unmuted participant minute”?

Unmuted participant minutes are calculated using the number of participants who have their microphone unmuted during a call (regardless of if they are speaking), multiplied by the length of the meeting.

For example, a 60 minute meeting with 3 participants, where only 2 participants were unmuted and the third participant was muted for the whole meeting, would use 120 unmuted participant minutes.

Two features for the price of one

If you choose to use both Session Transcriptions and Live Captions in the same video call session, you will only be charged once per unmuted participant minute at $0.024.

See Embedded pricing