Video avatar mode
In video avatar mode, the character in a voice simulation appears as a lifelike, lip-synced face inside a video call. The learner talks out loud, and the face moves with the character's voice as it answers. Everything else about the run stays the same: the conversation, the transcript, the feedback report and the grade.
What the learner sees
The run uses the Video call layout: a video-meeting screen with the character on the stage and the learner as a participant. Where the character's photo would sit, the learner sees a moving face that speaks the character's lines.
- While the face connects, the learner sees the character's picture and “Connecting to the video avatar…”.
- The call has the usual voice controls, captions and self-view. The learner's own camera stays off until they turn it on, and nothing from it is transmitted or recorded.
- The face is a ready-made face matched to the character's gender. It is not generated from the Character photo you chose.
For everything else the learner experiences in a voice run, see What a voice simulation is like for the learner.
If the face cannot connect
If the video face cannot start, or drops during the run, the call does not stop. The character falls back to their picture, and the learner keeps hearing the character's voice and talking as before. The conversation, the transcript and the report are not affected.
How to get it
Video avatar mode is not something you switch on yourself. Two things have to happen, and Cesura does both:
- Cesura enables video avatars for your organization.
- Cesura sets each simulation that should use it to video avatar mode.
To use it, ask your Cesura contact and name the simulations you want in video mode, and ask about pricing at the same time.
Video avatars are not available to organizations that run on their own AI provider, because the video face runs on Cesura’s account. A learner on such a simulation gets the voice call with the character’s picture instead, and sees “Video is not available for your organization, so this conversation shows the character’s picture instead.” See Run simulations on your own AI provider account (BYOK).
Once a simulation is in video mode, its Delivery Mode tab shows Lifelike video avatar under Choose Audio Experience. You can still edit and save the simulation as usual. If you switch it to another experience, only Cesura can switch it back.
Before you share it
- Test the simulation once yourself from a testing space, on the kind of device your learners use.
- Video needs a stable connection. Ask learners to use a reliable network and headphones.
- Video avatar runs are voice runs, so they are capped at 20 minutes and charged as two runs.