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.

​
Prompt Settings

These settings appear below the system prompt editor:
SettingOptionsDefault
Enhanced Turn TakingOn / OffOff
Prompt EnhancerDisabled / Basic / AdvancedBasic
Enhanced Turn Taking enables better numeral capturing and backchannel detection for more natural conversations. Prompt Enhancer applies automatic enhancements to your prompt. Basic adds stable model-agnostic improvements; Advanced adds model-aware prompts with live context.

​
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.
SettingRangeDefault
Expressiveness0.0–2.01.0
Voice DictionariesMulti-selectNone
STT ModelHamsa-STT-S2 / S3-beta / EnglishHamsa-STT-S2
→ See Voice Settings for full details.

​
Call Behavior Settings

SettingRangeDefault
Wait for User to Speak FirstNever / Always / Outbound onlyNever
User Gender DetectionOn / OffOff
Smart Call EndOn / OffOff
Language/Dialect SwitcherOn / OffOff
InterruptOn / OffOn
Ambient SoundOn / OffOff
Thinking VoiceOn / OffOff
Speaker Identification (Beta)On / OffOff
Response Delay100–1500ms400ms
User Inactivity Timeout5–60s15s
Max Call Duration30s – 1 hour5 min
Minimum Interruption Duration0.2–1.5s0.5s
VAD Activation Threshold0.2–0.90.5
→ See Call Behavior for full details. → See Intelligence Features for details on Gender Detection, Smart Call End, Speaker Identification, and Language/Dialect Switcher.

​
LLM Settings

SettingOptionsDefault
ProviderOpenAI, Gemini, Groq, DeepMyst, CustomGemini
ModelVaries by providerGemini 3.1 Flash Lite
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.

​
Noise Cancellation

Removes background noise from the caller’s audio.
SettingOptionsDefault
ModelDisabled / Telephony Optimized / General Use CasesDisabled
Strategy (when enabled)Per Conversation / Per TurnPer Conversation
Auto Gain ControlOn / OffOff
Send Denoised to STTOn / OffOff
Ambient Sound — Adds subtle ambient sound to the agent’s audio. Do not combine with Noise Cancellation. Thinking Voice — Plays a thinking/processing sound between responses.

​
Intelligence Features

FeatureDescription
Gender DetectionDetects caller’s likely gender for appropriate speech forms (helpful for Arabic)
Smart Call EndAutomatically ends the call when the conversation concludes naturally
Speaker Identification (Beta)Distinguishes multiple speakers on the same call
Agentic RAGAgent decides when to search the knowledge base for improved accuracy
Language Dialect SwitcherSwitches language or dialect instantly when the user requests
→ 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