What is LLM Configuration?
The Language Model (LLM) is the brain of your voice agent, powering conversation understanding, response generation, and decision-making. You can choose which model to use and adjust temperature to tune how consistent or varied the responses are.Supported LLM Providers:
- OpenAI — GPT-5, GPT-4.1, GPT-4o (and Mini/Nano variants)
- Gemini — Gemini 2.5 Pro, Gemini 2.5 Flash
- DeepMyst — Voice-optimized GPT-4.1 models
- Groq — OSS models
- Custom — Self-hosted or third-party models via OpenAI-compatible API
Configuration Parameters
Model Selection Choose the model that fits your performance and latency requirements. Nano/Flash variants are faster and cost less; Pro/full variants offer higher reasoning quality. Temperature (0.0 – 1.0) Controls randomness in responses. Lower values produce more consistent, predictable outputs; higher values produce more varied, natural-sounding responses. Default is 0.2.For GPT-5 family models (GPT-5, GPT-5-Mini, GPT-5-Nano), temperature is fixed at 1.0 and cannot be changed.
Getting Started
Single Prompt Agents
Configure LLM in the single prompt agent settings.
Set via API
Configure LLM settings programmatically.
Learn More
Single Prompt Agents
Configure LLM for Single Prompt Agents
Flow Agents
Set LLM parameters in Flow Agents