LLM Tab
The LLM Tab allows you to configure the “brain” of your voice AI agent. You can select the provider and specific model that best fits your latency and intelligence requirements.Supported LLM Models
OpenAI (Industry Leader)
- GPT-4o: Highly intelligent, multimodal. Best for complex reasoning.
- GPT-4o-mini: Specialized for speed and cost-effectiveness. Recommended for most voice agents.
Anthropic (Nuanced Conversation)
- Claude 3.5 Sonnet: Excellent at following strict instructions and handling multi-step logic.
Deepgram/Groq (Lowest Latency)
- Llama 3.1 (70B/8B): Open-source models optimized for inference speed. Best for extremely fast, conversational pacing.
Key Configurations
1. Temperature
Controls the “creativity” or “randomness” of the agent’s output.- Low (0.0 - 0.3): Highly consistent and factual. Recommended for technical support or bank agents.
- Medium (0.4 - 0.7): Balanced. Good for general customer service.
- High (0.8 - 1.0): More varied responses. Good for storytelling or informal chat.