Autonomous silence detection

Technical documentation for the autonomous_silence_handling feature.

Overview

Autonomous Silence Handling is a feature that allows the AI agent to intelligently detect and respond to prolonged silence during a call. When enabled, the agent will:

Detect when the caller has stopped speaking

Prompt the caller to check if they're still on the line

After multiple attempts without response, gracefully end the call

This prevents calls from hanging indefinitely when callers walk away, get disconnected, or put the phone down.

Configuration

Agent Schema

{
  "autonomous_silence_handling": true
}

Field	Type	Default	Description
`autonomous_silence_handling`	boolean	`false`	Enable/disable autonomous silence detection

Automatic Tool Addition

When autonomous_silence_handling is enabled, the system automatically adds the end_call tool to the agent's toolset if not already present. This ensures the agent can hang up after detecting prolonged silence.

How It Works

Timing Configuration

Parameter	Value	Description
`first_silence_check`	7 seconds	Time before first prompt after silence detected
`silence_check_interval`	12 seconds	Time between subsequent prompts
`max_silence_attempts`	3	Maximum prompts before instructing agent to hang up

State Machine

[User Speaking] → [User Away] → [Silence Check 1] → [Silence Check 2] → [Silence Check 3] → [Hang Up]
       ↑              │                │                   │                   │
       └──────────────┴────────────────┴───────────────────┴───────────────────┘
                              (User speaks → reset timer)

Event Flow

User State: "away" - Silence timer starts

7 seconds pass - First silence check triggered

Agent speaks - "Are you still there?" (contextual)

12 more seconds - Second silence check

Agent speaks - "I'm still here if you need me"

12 more seconds - Third and final check

Agent speaks - Brief goodbye + calls end_call tool

Contextual Prompts

The agent receives different instructions based on the attempt number:

Attempt 1:

IMPORTANT: No speech detected from caller. This is attempt 1 of 3.
Based on context: if they said they need to look something up, say you'll wait.
Otherwise, ask a short question to check if they are still on the line.

Attempt 2:

IMPORTANT: Still no speech from caller. This is attempt 2 of 3.
Ask one more time if they are still there.
If no response after this, you will need to end the call.

Attempt 3 (Final):

IMPORTANT: No speech detected from caller for a long time.
This is attempt 3 of 3.
You must now say a brief goodbye and immediately use end_call to hang up.

Key Behaviors

No check while agent speaking: Silence timer pauses when agent is speaking

Reset on user speech: Any detected user speech resets the timer and attempt counter

Graceful termination: Agent is instructed to say goodbye before hanging up

Context-aware: First prompt considers conversation context (e.g., "let me look that up")

Use Cases

Good For

Reception/Front Desk: Callers may walk away to check something

Customer Support: Long hold times while customers search for info

Appointment Booking: Callers checking their calendars

Consider Disabling For

Emergency Lines: May need to stay connected even during silence

Listening Services: Where silence is expected and acceptable

IVR/Menu Systems: Where users navigate with keypresses, not speech

Interaction with Other Features

With `voicemail_detection`

Both can be enabled simultaneously. Voicemail detection triggers first (on initial greeting), while silence handling activates during the conversation.

With `max_duration_seconds`

If max_duration_seconds is set, the call will end at that time regardless of silence handling state.

With `end_call` Tool

If the agent already has end_call in its tools, no duplicate is added. The silence handling instructions simply tell the agent to use the existing tool.

Webhook Events

When a call ends due to silence handling:

{
  "message": {
    "type": "end-of-call-report",
    "call": {
      "status": "ended"
    },
    "summary": "Call ended after no response from caller..."
  }
}

The status-update webhook will show status: "ended" (not a special silence-related status).

Troubleshooting

Agent Not Detecting Silence

Verify autonomous_silence_handling: true is in the agent configuration

Check the call transcript to see if silence detection prompts appear

Ensure STT (Speech-to-Text) is properly configured to detect when user stops speaking

Agent Ending Calls Too Quickly

The 7-second initial delay should prevent premature endings

Review the call transcript to see timing of silence prompts

Note that timing parameters (7s, 12s, 3 attempts) are currently fixed

Agent Not Hanging Up After 3 Attempts

The end_call tool is automatically added when silence handling is enabled

Review the end-of-call-report to see if the agent attempted to end the call

The LLM may occasionally not follow instructions perfectly - this is expected behavior with AI agents

Autonomous silence detection

Overview#

Configuration#

Agent Schema#

Automatic Tool Addition#

How It Works#

Timing Configuration#

State Machine#

Event Flow#

Contextual Prompts#

Key Behaviors#

Use Cases#

Good For#

Consider Disabling For#

Interaction with Other Features#

With voicemail_detection#

With max_duration_seconds#

With end_call Tool#

Webhook Events#

Troubleshooting#

Agent Not Detecting Silence#

Agent Ending Calls Too Quickly#

Agent Not Hanging Up After 3 Attempts#