Step1 - Send text messages to recreate an existing emotional state from a previous conversation.
Custom message:
Predefined messages
Step 2 - Generate emotional voices controlled by the Emo-Matrix.
The initial Emo Voice generation will take 2 seconds, and subsequent messages will be faster, their speed
depending on the length. Our MetaSoul introduces only a 100ms delay to Microsoft Speech. For long messages, it is
recommended to send them separately, using punctuation as a separator. This approach enables MetaSoul to adjust the
tone of the voice progressively throughout the lengthy message and reducing overall delay.
Select Voice Type:
Send text to be generated in audio to Emo Matrix:
Include Blend Shapes along with visemes in response:
Select AI Model to use:
Select Emotion Intensity (COEF):
%
a) Emo Voice (Simple text audio controlled by the Emo-Matrix):
b) OpenAI response with a voice controlled by the Emo-Matrix: