Help for Private Practices / Text-to-Speech
Text-to-Speech (TTS)
In some scenarios, avatars can be displayed as guests. In the scenario descriptions, this is indicated by “Let avatars speak individually with patients”.
1
2
Select an Avatar
- In the upper area of the TTS window, you will see a selection of avatars.
- Click the avatar that should speak. The selected avatar is highlighted.
- Use the horizontal slider to scroll through all available characters.
3
Enter Text
- Type your desired text into the large white input field at the bottom.
- Click “Add Text”
– to add the text to the list above, or
– to move an existing list entry back into the white input field.
- In the list, the text appears with a green play button for playback and a red X for deleting.
Set the Tone
The avatars’ voices are AI-generated. You describe how a text should be read aloud in square brackets at the very beginning of the text.
Examples:
[calm and friendly] Good morning, it’s nice to have you here.
[annoyed and loud] Can’t you hurry up? I’ve been waiting forever!
[whispering] Look, over there.
Without a specification in brackets, the AI determines the tone automatically.
4
Playback
To play a text, click the green play button next to the desired text.
The selected avatar reads the text aloud.
Additional Tips:
- Prepare frequently used texts in advance and save them as a text file. During the session, you can quickly paste them in without having to type.
- The voices are AI-generated and match the selected avatar. You set the tone with a description in square brackets at the beginning of the text.
- The function is particularly suitable for conversation training, role-plays and confrontation with specific statements.
No Sound?
- Check whether the volume control on the VR headset is also turned up.
Switch the avatar and try again.

