CreatorsAGI Documentation
  • Welcome to CreatorAGI
  • Why CreatorsAGI Stands Apart?
  • Why Partner with CreatorsAGI?
  • Creator Pricing and Subscriptions
  • Product Walk Through
  • Mobile App Tour
  • Creator Portal Guide
    • Setting up Creator Account
    • Setting up Stripe Payments
    • What is an AI Companion?
    • Creating a new AI Companion
    • Create Audio AI Companions
    • Adding Knowledge to AI Companion
    • Testing your AI Companion
    • Publishing your AI Companion
    • Creator Subscriptions and Payments
    • Go Live with Your First AI Companion
    • Steps by Step Walkthrough
    • Crafting Powerful Instructions for Your AI Companion
  • AI Companion User Guide
    • Overview
    • CreatorsAGI Home
    • Setting up Your Account
    • AI Companions published by Creators
    • Conversation with AI Companion
      • Elements of an AI Chat
      • Message Actions
      • Bookmarking messages
      • Conversation Profile Icon
      • Clearing the conversation
      • Switch to another companion
    • Settings Page
    • Crafting Effective Prompts
    • User Subscription Plans
  • Page
  • FAQs
    • FAQs
    • Creator Specific FAQs
    • Mobile App FAQs
  • Contact US
  • CreatorsAGI Data and AI
Powered by GitBook
On this page
  • Audio AI Companion - Configuration Guide
  • Key Features and Adjustable Settings
  • Other Configurable Options
  • Usage Tips

Was this helpful?

  1. Creator Portal Guide

Create Audio AI Companions

PreviousCreating a new AI CompanionNextAdding Knowledge to AI Companion

Last updated 6 months ago

Was this helpful?

Audio AI Companion - Configuration Guide

The Audio AI Editor enables creators to create and customize the behavior of live audio AI Companions using various configuration settings.

Key Features and Adjustable Settings

1. Voice Activity Detection (VAD)

Voice Activity Detection determines when the system detects speech in an audio stream.

  • Duration (Milliseconds): Configure the time window for detecting voice activity, ranging from 200 ms to 2000 ms.

  • How It Works:

    • A shorter duration makes VAD more sensitive to brief sounds.

    • Longer durations are useful for capturing sustained speech while reducing noise interference.

2. Audio Silence Threshold

The silence threshold sets the minimum audio level required for the system to detect voice input.

  • Threshold: A value between 0.2 and 1.0.

  • How It Works:

    • Lower thresholds (e.g., 0.2) make the system sensitive to softer sounds.

    • Higher thresholds (e.g., 1.0) ensure only loud or prominent sounds are captured, filtering background noise.

Other Configurable Options

  • Creativity (Temperature): Adjusts the system's randomness in generating outputs (Between 0-2). Higher values (e.g., 1.7) produce more creative responses, while lower values generate more deterministic outputs.

  • Word Diversity (Top P): Controls how diverse or focused the generated responses are (Between 0-1). Lower values ensure more relevant and concise outputs.

  • Voice Model: Allows selection from available AI voice models (e.g., "coral") for tailoring audio output styles.


Usage Tips

  • Optimizing VAD Settings: Experiment with the duration to find the ideal balance between responsiveness and accuracy for your use case.

  • Fine-Tuning Silence Threshold: Use a lower threshold in quiet environments to capture all audio and a higher threshold in noisy spaces to focus on clear speech.

  • Preview and Test: Always test your configurations in the "Test" or "Preview" section to ensure your settings meet project requirements.