Skip to main content

Overview

Call behavior settings control the timing, flow, and interaction dynamics of your voice agent conversations. These settings directly impact caller experience, conversation efficiency, and perceived naturalness of your AI agent.
Key Call Behavior Settings:
  • Response delay (how quickly agent responds)
  • Interruption handling (can users interrupt?)
  • User inactivity timeout (handling silent callers)
  • Max call duration (preventing runaway calls)
  • Background ambient sound
  • Thinking voice (natural pauses)

Response Delay

What is Response Delay?

Response delay determines how long the agent waits after detecting that the user has stopped speaking before generating a response. Technical Definition: The minimum number of milliseconds between when the system detects speech has ended and when it begins processing the response.

Configuration

Range: 100ms - 1500ms Default: 400ms Increment: 100ms To configure:
  1. Open Call Settings section
  2. Locate Response Delay slider
  3. Adjust value (shows in milliseconds)
  4. Current value displays next to slider
  5. Save changes

Impact on Conversation Flow

Lower Values (100-300ms): Advantages:
  • Very responsive, snappy conversations
  • Feels more dynamic and engaging
  • Efficient for simple Q&A
  • Better for impatient callers
⚠️ Disadvantages:
  • May cut off users who pause naturally
  • Can interrupt multi-part questions
  • Feels rushed for some users
  • May miss end of long answers
Medium Values (400-600ms): Advantages:
  • Balanced, natural conversation pace
  • Allows brief pauses without cutting off
  • Works for most use cases
  • Professional feel
⚠️ Disadvantages:
  • May feel slightly slow for rapid exchanges
  • Not ideal for very simple interactions
Higher Values (700-1500ms): Advantages:
  • Very thoughtful, deliberate responses
  • Great for users who speak slowly or pause
  • Better for complex topics requiring thought
  • Comfortable for elderly or non-native speakers
⚠️ Disadvantages:
  • Can feel slow or unresponsive
  • Inefficient for simple questions
  • May frustrate fast-paced callers
Start with the default 400ms. Adjust based on testing with your actual target audience and use case.

Response Delay by Use Case

Customer Support (Quick Inquiries)
  • Recommended: 300-400ms
  • Reasoning: Efficiency matters, questions are usually straightforward
  • Example: “What are your hours?” → Quick response expected
Technical Support (Complex Troubleshooting)
  • Recommended: 500-700ms
  • Reasoning: Users need time to describe issues, check things
  • Example: “My device shows error X when I…” → User may pause to read error
Sales Calls
  • Recommended: 300-500ms
  • Reasoning: Dynamic conversation, but allow for objection handling
  • Example: Balance between energy and letting prospects speak
Healthcare/Medical Scheduling
  • Recommended: 600-800ms
  • Reasoning: Callers may be elderly, anxious, or need time to find information
  • Example: “Let me find my insurance card…” → Needs patience
Surveys/Feedback Collection
  • Recommended: 700-1000ms
  • Reasoning: People need time to think about answers
  • Example: “On a scale of 1-10…” → Requires contemplation
Appointment Booking
  • Recommended: 400-600ms
  • Reasoning: Moderate pace for checking calendars
  • Example: “Let me check my calendar…” → Brief pause acceptable
Legal/Compliance Information
  • Recommended: 600-900ms
  • Reasoning: Complex information, users may need to take notes
  • Example: Delivering important terms → Don’t rush

Testing Response Delay

Test Scenarios:
  1. Natural Pausers: Have someone who pauses mid-sentence test
  2. Fast Talkers: Have rapid speakers test for cut-offs
  3. Question Sequences: “I have two questions…” (does it wait?)
  4. Listing Items: “I need help with X, Y, and Z” (catches all three?)
  5. Thinking Out Loud: “So I’m wondering…” (patient enough?)
Response delay is highly subjective. What feels natural to you may feel slow or fast to your callers. Always test with real users from your target demographic.

Interruption Handling

What is Interruption?

Interruption handling determines whether users can speak while the agent is speaking, cutting off the agent’s response. Enabled (Default): Users can interrupt the agent naturally Disabled: Agent completes full response before listening again

Configuration

To enable/disable:
  1. Open Call Settings section
  2. Find Interrupt toggle
  3. Toggle on (enabled) or off (disabled)
  4. Save changes

When Interruptions are Enabled

Behavior:
  • Agent speaks response
  • User starts speaking
  • Agent immediately stops and listens
  • Agent acknowledges interruption (optional)
  • User completes their input
  • Agent responds to new input
Example Flow:
Agent: "Our business hours are Monday through Friday, 9 AM to—"
User: "Actually, I need weekend hours"
Agent: [stops speaking] "For weekend hours, we're open Saturday..."
Best For:
  • Customer service conversations
  • Sales calls (engagement is key)
  • Support where users may have urgent questions
  • Natural, human-like conversations
  • Interactive Q&A sessions
Advantages:
  • Natural conversation flow
  • Users don’t have to wait for full response
  • Better for correcting misunderstandings
  • More engaging experience
⚠️ Considerations:
  • Agent may be cut off before delivering full message
  • Important information could be missed
  • May be interrupted by background noise

When Interruptions are Disabled

Behavior:
  • Agent speaks complete response
  • User speaking during this time is ignored
  • After agent finishes, system listens for user input
  • User must wait for agent to complete
Example Flow:
Agent: "Our business hours are Monday through Friday, 9 AM to 6 PM,
       and Saturday 10 AM to 4 PM. We're closed on Sundays."
User: [tries to speak but agent continues]
Agent: [finishes complete response]
System: [now listening for user input]
User: "What about holidays?"
Best For:
  • Critical information delivery
  • Legal disclaimers
  • Compliance statements
  • Step-by-step instructions
  • Confirmation of important actions
  • Medical information
  • Safety warnings
Advantages:
  • Ensures complete information delivery
  • No partial messages
  • Better for structured scripts
  • Clearer for complex multi-step instructions
⚠️ Considerations:
  • Feels less natural
  • Frustrating if agent is verbose
  • Users may want to interject
  • Less engaging conversation
You can disable interrupts globally but still allow them for specific situations in your prompt. Example: “Users cannot interrupt normally, but if they say ‘stop’ or ‘wait’, acknowledge immediately.”

Mixed Approach (Prompt-Based)

Even with interrupts enabled, you can guide behavior in your prompt:
# Interruption Handling

Allow users to interrupt naturally during normal conversation.

However, for critical information, say:
"Let me share some important information - I'll need about 30 seconds."

Then deliver the critical information. Users are less likely to interrupt
when they know it's important and time-bounded.

Interruption Handling by Use Case

Use CaseRecommendationReasoning
Customer SupportEnabledNatural conversation, user needs matter most
Sales CallsEnabledEngagement is critical, handle objections quickly
Technical SupportEnabledUser may need to clarify or correct
Appointment BookingEnabledUser may realize conflict mid-confirmation
SurveysDisabledComplete each question clearly
Legal/ComplianceDisabledMust deliver full disclaimers
Medical InformationDisabledCritical safety information
IVR MenuDisabledUser needs to hear all options
AnnouncementsDisabledImportant broadcast information
Emergency AlertsDisabledCritical instructions must be heard
For most conversational agents, keep interrupts enabled for a natural experience. Only disable for specific compliance or information delivery scenarios.

User Inactivity Timeout

What is Inactivity Timeout?

The number of seconds of silence before the agent proactively reaches out to check if the user is still there. Purpose: Handle situations where:
  • User stepped away
  • User is confused or doesn’t know what to say
  • Connection issues
  • User is multitasking (looking for information)

Configuration

Range: 5-30 seconds Default: 15 seconds Increment: 1 second To configure:
  1. Open Call Settings section
  2. Locate User Inactivity Timeout slider
  3. Adjust value (shows in seconds)
  4. Save changes

How It Works

Flow:
  1. User stops speaking
  2. Agent responds (if applicable)
  3. Silence begins
  4. After [timeout] seconds of silence:
    • Agent proactively asks if user is still there
    • “Are you still there?”
    • “Is there anything else I can help with?”
    • “I’m here whenever you’re ready.”
  5. If user responds: Continue conversation
  6. If still silent: Repeat or end call (configurable in prompt)

Timeout Duration Guidelines

Short Timeouts (5-10 seconds): Good For:
  • High-volume call centers
  • Simple transactional interactions
  • Efficient, quick exchanges
  • Queue management scenarios
⚠️ Watch Out:
  • May feel rushed
  • Not enough time to look up information
  • Frustrating for multi-tasking users
Medium Timeouts (15-20 seconds): Good For:
  • General customer service
  • Balanced approach
  • Most business use cases
  • Default recommendation
⚠️ Watch Out:
  • May be too long for simple interactions
  • May be too short for complex lookups
Long Timeouts (25-30 seconds): Good For:
  • Complex information gathering (user checking documents)
  • Elderly or deliberate callers
  • Healthcare/medical (finding insurance cards)
  • Technical support (checking error messages)
⚠️ Watch Out:
  • Very long silence can feel awkward
  • Inefficient for simple calls
  • May indicate dropped connection
Don’t set timeout too short (<10s) unless you have a specific reason. Users often need time to check calendars, find information, or think about responses.

Inactivity Timeout by Use Case

Customer Support (General)
  • Recommended: 15-20 seconds
  • Reasoning: Balanced patience, not too rushed
  • Poke Message: “I’m still here if you need anything else.”
Technical Support
  • Recommended: 20-30 seconds
  • Reasoning: Users may be checking error messages, cables, settings
  • Poke Message: “Take your time. Let me know when you’re ready.”
Appointment Booking
  • Recommended: 15-25 seconds
  • Reasoning: Users checking calendars
  • Poke Message: “I’ll wait while you check your schedule.”
Sales/Lead Qualification
  • Recommended: 10-15 seconds
  • Reasoning: Keep momentum, but allow thinking
  • Poke Message: “Do you have any questions I can answer?”
Surveys
  • Recommended: 20-30 seconds
  • Reasoning: People need time to think about ratings/feedback
  • Poke Message: “Take your time to think about your answer.”
Quick Info Lookup
  • Recommended: 5-10 seconds
  • Reasoning: Simple questions, quick answers
  • Poke Message: “Is there anything else you need?”

Customizing Poke Messages

Define how your agent handles silence in your prompt:
# Handling Silence

After 15 seconds of silence:
First time: "I'm still here. Take your time if you're looking something up."
Still silent: "No rush! I'm here whenever you're ready."
Extended silence (30s+): "I'll let you go for now. Feel free to call back anytime!"

Then end the call gracefully.
Poke Message Best Practices:
  • Be reassuring, not demanding
  • Acknowledge they may be busy (“looking something up”)
  • Offer to wait or call back
  • Don’t make user feel bad about silence
Use the pokeMessages array in your configuration to define multiple poke messages. The system will use them in sequence for repeated silence periods.

Max Call Duration

What is Max Call Duration?

The maximum length of time (in seconds) a call can last before being automatically terminated. Purpose:
  • Prevent runaway costs
  • Handle stuck calls
  • Set clear boundaries
  • Protect against infinite loops

Configuration

Range: 30-600 seconds (0.5 - 10 minutes) Default: 300 seconds (5 minutes) Increment: 10 seconds To configure:
  1. Open Call Settings section
  2. Locate Max Call Duration slider
  3. Adjust value (shows in seconds)
  4. Save changes

How It Works

Flow:
  1. Call begins
  2. Timer starts
  3. At [max duration - 30s]: Agent warns (optional via prompt)
    • “We have about 30 seconds left. Is there anything else?”
  4. At [max duration]: Call ends with farewell message
  5. Call terminates gracefully
Max call duration is a safety net, not a target. Most calls should end naturally via Smart Call End or user ending the conversation.

Duration Guidelines by Use Case

Quick Transactions (30-120 seconds)
  • Use Cases: Balance check, hours lookup, simple FAQ
  • Why: Simple information, in and out
  • Example: “What are your hours?” → 45 second call
Standard Conversations (120-300 seconds)
  • Use Cases: Customer support, appointment booking, basic troubleshooting
  • Why: Moderate complexity, multiple steps
  • Example: Schedule appointment → 2-3 minute call
Extended Support (300-600 seconds)
  • Use Cases: Technical troubleshooting, detailed sales, consultations
  • Why: Complex issues require time
  • Example: Troubleshoot device → 5-7 minute call
Surveys/Feedback (120-240 seconds)
  • Use Cases: Customer satisfaction surveys, feedback collection
  • Why: Multiple questions, time to think
  • Example: 10-question survey → 3-4 minutes
Setting max duration too low creates poor user experience. Set it 20-30% higher than your expected average call duration to allow for edge cases.

Max Duration Recommendations

Use CaseRecommended MaxAverage ExpectedBuffer
Balance/Hours Check60s30-40s2x
Simple FAQ90s45-60s1.5x
Appointment Booking240s120-180s1.3x
Customer Support360s180-240s1.5x
Technical Support480s240-360s1.3x
Sales Qualification300s180-240s1.3x
Detailed Survey300s180-240s1.3x
Complex Consultation600s360-480s1.3x

Handling Max Duration in Prompts

Prepare for approaching time limit:
# Max Call Duration Handling

The system will notify you when 60 seconds remain.

At that point:
"I want to make sure I help you before our time is up. What's the most
important thing I can help you with right now?"

If user has additional needs:
"I can schedule a callback or transfer you to someone who can continue
helping you. Which would you prefer?"

At max duration:
"I need to wrap up our call now. Here's a summary of what we covered: [brief summary]
Thank you for calling!"
Always provide a graceful exit before max duration. Users shouldn’t feel abruptly cut off.

Monitoring Call Duration

Use analytics to optimize max duration: Metrics to track:
  • Average call duration
  • % of calls hitting max duration
  • Completion rate vs. duration
  • User satisfaction vs. duration
Optimization:
  • If >5% of calls hit max: Increase limit
  • If average is <50% of max: Consider decreasing for efficiency
  • If abandonment increases near max: Add warning prompts

Background Noise (Ambient Sound)

What is Background Noise?

Adds subtle ambient sound to the agent’s audio to create a more human, realistic environment. Purpose:
  • Reduce “dead air” feeling
  • Simulate call center environment
  • Make AI feel more human
  • Provide auditory continuity

Configuration

Options:
  • Disabled (Default): Pure AI voice, no background
  • Enabled: Subtle background ambiance
To enable:
  1. Open Call Settings section
  2. Find Ambient Sound toggle
  3. Enable or disable
  4. Save changes

When to Use Background Noise

Good Use Cases: Call Center Simulation
  • Agent positioned as call center representative
  • Simulates realistic environment
  • Reduces AI “uncanny valley”
Brand Consistency
  • Match existing IVR or call center sound
  • Consistent experience across channels
Reducing Dead Air
  • Some users find complete silence uncomfortable
  • Gentle background provides continuity
⚠️ Avoid Background Noise When: Professional/Premium Brands
  • High-end brands may want “perfect” audio
  • Background noise can seem cheap
Technical Clarity Required
  • Medical information
  • Legal disclaimers
  • Complex instructions
Using Noise Cancellation
  • Creates processing artifacts
  • Conflicts with noise removal
International Calls
  • Poor connections already have noise
  • Adding more degrades quality
Do not enable both Background Noise and Noise Cancellation. They conflict and create audio artifacts.

Background Noise Characteristics

Sound Type:
  • Subtle office ambiance
  • Very low volume (not distracting)
  • Consistent throughout call
  • No specific identifiable sounds
Volume:
  • Mixed at -30dB to -40dB below voice
  • Barely noticeable but present
  • Never interferes with speech clarity
Background noise is subtle by design. If you can clearly hear it, it’s too loud. It should be almost subliminal.

Thinking Voice

What is Thinking Voice?

Adds natural pauses and verbal fillers to make the agent sound more human and thoughtful. Examples:
  • “Hmm…”
  • “Let me see…”
  • “Okay…”
  • “Ah, yes…”
  • Natural pauses before responses

Configuration

Options:
  • Disabled (Default): Direct, efficient responses
  • Enabled: Natural pauses and fillers
To enable:
  1. Open Call Settings section
  2. Find Thinking Voice toggle
  3. Enable or disable
  4. Save changes

How Thinking Voice Works

Without Thinking Voice:
User: "What are your hours?"
Agent: [immediate] "We're open Monday through Friday 9 AM to 6 PM."
With Thinking Voice:
User: "What are your hours?"
Agent: [brief pause] "Let me check that for you...
       We're open Monday through Friday, 9 AM to 6 PM."

Benefits of Thinking Voice

Advantages: More Human-Like
  • Mimics natural human behavior
  • People pause before answering
  • Reduces “AI” feeling
Gives Processing Time
  • Makes latency feel intentional
  • Covers technical delays gracefully
  • Users more patient when agent “thinks”
Better Conversation Flow
  • Natural transitions between topics
  • Less jarring subject changes
  • Feels more thoughtful
Reduces Pressure
  • Users don’t feel rushed
  • Comfortable pauses in conversation
  • Time to process information
⚠️ Disadvantages: Slower Conversations
  • Adds 1-3 seconds per response
  • Less efficient
  • Longer call durations
May Seem Less Professional
  • Some contexts demand crisp responses
  • Can seem uncertain or hesitant
  • May reduce authority perception
Not Suitable for All Use Cases
  • Technical information delivery
  • Time-sensitive scenarios
  • High-volume quick transactions

Thinking Voice by Use Case

Use CaseRecommendationReasoning
Friendly Customer SupportEnabledNatural, human conversation
Corporate HelpdeskDisabledProfessional, efficient
Healthcare SchedulingEnabledWarm, caring approach
Technical SupportDisabledClarity and precision
Sales CallsEnabledNatural rapport building
Legal InformationDisabledAuthority and confidence
SurveysEnabledCasual, comfortable
Emergency/UrgentDisabledDirect, immediate
Appointment RemindersDisabledClear, concise
Lead QualificationEnabledConversational discovery
Enable Thinking Voice for conversational, relationship-focused interactions. Disable for professional, information-delivery scenarios.

Combining Thinking Voice with Other Settings

Natural Conversation Setup:
Response Delay: 500-600ms
Interrupt: Enabled
Thinking Voice: Enabled
Background Noise: Optional
Creates very human-like, natural conversation. Efficient Professional Setup:
Response Delay: 300-400ms
Interrupt: Disabled (for important info)
Thinking Voice: Disabled
Background Noise: Disabled
Creates crisp, professional, efficient interaction.

Call Behavior Presets

Preset 1: Friendly Customer Service

Configuration:
Response Delay: 400ms
Interrupt: Enabled
Inactivity Timeout: 20s
Max Call Duration: 360s (6 minutes)
Background Noise: Optional
Thinking Voice: Enabled
Best For: General customer support, hospitality, retail

Preset 2: Professional Corporate

Configuration:
Response Delay: 500ms
Interrupt: Disabled (for critical info)
Inactivity Timeout: 15s
Max Call Duration: 300s (5 minutes)
Background Noise: Disabled
Thinking Voice: Disabled
Best For: Corporate helpdesk, financial services, legal

Preset 3: Fast-Paced Sales

Configuration:
Response Delay: 300ms
Interrupt: Enabled
Inactivity Timeout: 10s
Max Call Duration: 300s (5 minutes)
Background Noise: Disabled
Thinking Voice: Disabled
Best For: Sales calls, lead qualification, outbound

Preset 4: Patient Healthcare

Configuration:
Response Delay: 700ms
Interrupt: Disabled
Inactivity Timeout: 30s
Max Call Duration: 480s (8 minutes)
Background Noise: Disabled
Thinking Voice: Enabled
Best For: Healthcare, elderly care, complex scheduling

Preset 5: Technical Support

Configuration:
Response Delay: 600ms
Interrupt: Enabled
Inactivity Timeout: 25s
Max Call Duration: 600s (10 minutes)
Background Noise: Disabled
Thinking Voice: Disabled
Best For: Technical troubleshooting, IT support

Testing Call Behavior

Test Scenarios

Scenario 1: Interruption Test
  1. Have agent give long response
  2. Interrupt mid-sentence
  3. Verify agent stops and listens
  4. Verify it responds to interruption
Scenario 2: Silence Test
  1. Don’t respond after agent speaks
  2. Wait for inactivity timeout
  3. Verify poke message triggers
  4. Verify handling of continued silence
Scenario 3: Long Call Test
  1. Engage in conversation
  2. Approach max duration
  3. Verify warning (if configured)
  4. Verify graceful end at max duration
Scenario 4: Response Timing Test
  1. Ask questions with different natural pauses
  2. Check for premature responses
  3. Check for awkwardly long waits
  4. Adjust response delay accordingly
Scenario 5: Multi-Part Question Test
  1. Ask: “I have two questions about X and Y”
  2. Verify agent waits for complete question
  3. Verify agent addresses both parts

Measuring Success

Key Metrics: Completion Rate
  • % of calls where task is completed
  • Higher = better configuration
Average Call Duration
  • Should match expected duration for use case
  • Too long = inefficient
  • Too short = rushed/incomplete
Abandonment Rate
  • % of callers who hang up mid-call
  • High abandonment may indicate poor timing
User Satisfaction
  • Post-call surveys
  • Feedback on conversation flow
  • Natural vs. robotic feel
Repeat Questions
  • If users frequently repeat themselves
  • May indicate response delay too short
Track these metrics in your analytics dashboard and adjust settings based on real data, not assumptions.

Troubleshooting Common Issues

Agent Cuts Off Users Mid-Sentence

Problem: Agent responds before user finishes speaking Solution:
  • Increase Response Delay (+100-200ms)
  • Test with users who speak slowly or pause
  • Verify no echo/feedback creating false endpoints

Agent Feels Unresponsive

Problem: Long pauses after user speaks Solution:
  • Decrease Response Delay (-100-200ms)
  • Check LLM latency (may be model issue)
  • Verify adequate server resources

Users Complain About Being Rushed

Problem: Not enough time to think or respond Solution:
  • Increase Inactivity Timeout (+5-10s)
  • Enable Thinking Voice for more natural pace
  • Increase Response Delay slightly

Calls Frequently Hit Max Duration

Problem: >5% of calls reaching time limit Solution:
  • Increase Max Call Duration (+60-120s)
  • Review if agent is too verbose
  • Check for conversation loops

Users Interrupt Constantly

Problem: Frequent interruptions disrupting flow Solution:
  • Shorten agent responses in prompt
  • Keep responses to 20-30 seconds max
  • Use “Let me share important info” for critical sections

Poke Messages Feel Annoying

Problem: Users react negatively to timeout prompts Solution:
  • Increase Inactivity Timeout
  • Soften poke message language
  • Reduce frequency of repeat pokes

Next Steps


Need advanced control? Explore Flow Agent Call Settings for node-level behavior customization.