β¨Ask about our social endeavors and plansβ¨
Optimizes audio processing based on your microphone setup.
Choose the profile that best matches your microphone and environment.
Controls how the system detects when you start and stop speaking.
Choose the method for detecting speech activity.
Uses periods of silence to determine speech segments. Good for clear turn-taking.
How loud your voice needs to be to start detection. Higher values need louder audio (better for noisy places).
How much audio (in milliseconds) to include *before* detected speech starts. Helps catch initial sounds.
How long silence (in milliseconds) must last to consider speech ended. Shorter values detect turns faster.
Uses the meaning of words to detect when you've finished. Better for natural conversation flow and less likely to interrupt.
Controls how quickly the AI might interrupt or end a turn. 'Low' lets you speak longer; 'High' is faster to respond/chunk.