Skip to main content
This page is a quick reference for all settings available in the single prompt agent configuration panel. Each section links to a dedicated page with full details.

Voice Settings

Select a voice from Hamsa’s library, filtered by language, gender, dialect (Arabic only), and style. Language is set automatically when you choose a voice. → See Voice Settings for full details.

Call Behavior Settings

SettingRangeDefault
Response Delay100–1500ms400ms
InterruptOn / OffOn
User Inactivity Timeout5–60s15s
Max Call Duration30s – 1 hour5 min
Wait for User to Speak FirstNever / Always / Outbound onlyNever
Minimum Interruption Duration0.2–1.5s0.5s
VAD Activation Threshold0.2–0.90.5
→ See Call Behavior for full details.

LLM Settings

SettingOptionsDefault
ProviderOpenAI, Gemini, Groq, DeepMyst, CustomOpenAI
ModelVaries by providerGPT-4.1
Temperature0.0–1.00.2
Temperature controls response variability. Lower values produce more consistent outputs; higher values produce more natural-sounding variation.
GPT-5 family models (GPT-5, GPT-5-Mini, GPT-5-Nano) require temperature = 1.0. This is set automatically when you select a GPT-5 model.
→ See LLM Configuration for the full model list.

Audio Processing

Noise Cancellation — Removes background noise from the caller’s audio. Options: Disabled, Per Sentence, Per Conversation. Background Noise — Adds subtle ambient sound to the agent’s audio. Do not combine with Noise Cancellation. Thinking Voice — Adds natural filler words and pauses to the agent’s speech.

Intelligence Features

FeatureDescription
Gender DetectionDetects caller’s likely gender and injects context into the conversation
Smart Call EndAutomatically ends the call when the conversation concludes naturally
Speaker Identification (Beta)Distinguishes multiple speakers on the same call
Agentic RAGMulti-step reasoning for knowledge base retrieval
Language Dialect SwitcherAdapts Arabic speech recognition to the caller’s dialect
→ See Intelligence Features for full details.

Next Steps

Add Knowledge Base

Enhance your agent with reference documents

Integrate Tools

Connect custom functions and APIs

Configure Webhooks

Receive call events and data

Test Your Agent

Test before going live