User Defined Prompt:
Activation Word(s):
Advanced Settings
AI Model:
GPT-3.5 Turbo (Fastest, Cheapest)
GPT-4 Turbo (Faster, Cheaper)
GPT-4 (Standard)
Developer Prompt (appended to user prompt):
Voice:
Loading voices...
Max Tokens:
150
?
Controls response length. Lower = shorter, faster responses.
Temperature:
0.7
?
Controls creativity. Lower = more focused, higher = more creative.
Font Size:
24
px
?
Adjusts the size of the response text for better readability.
Avatar Scale:
0.6
?
Adjusts the overall size of the avatar. Lower values make it smaller.
Avatar Y Position:
-100
px
?
Adjusts the vertical position of the avatar. Positive values move it down, negative values move it up.
Presence Penalty:
0.0
?
Positive values encourage new topics, negative stick to context.
Frequency Penalty:
0.0
?
Positive values reduce repetition, negative encourage it.
Waiting Time (seconds):
3
?
How long to wait for more speech before generating a response.
Dialogue History Size:
5
?
Number of recent conversation exchanges to keep in context. Lower values reduce token usage.
Wait for Countdown
?
When enabled, generates response only after the countdown finishes instead of during silence.
Show Debug Window
?
Shows a window displaying the prompt, transcript, and other components being sent to the AI.
Phrase Activated Functions
Add New Function
Start Program
Debug Info
Sample debug information will appear here.
Total Prompt
System Prompt (includes Developer Prompt)
+
Dialogue History (includes current message)
Current Transcript
+
Computer Vision
Start Camera
Stop Camera
