### Answer Yes, you can configure the AI to stay silent for extended periods. Retell AI provides the

end_call_after_silence_ms

setting that controls how long the agent will wait before ending the call due to user silence. [(1) ]() [(2) ]() By default, this is set to 600,000 ms (10 minutes) , but you can adjust it. The minimum value allowed is 10,000 ms (10 seconds) , so you can extend it significantly beyond the default if needed. For your use case where you're sharing a scheduling link via SMS and want the AI to remain available while the lead completes the scheduling, you could: 1. Increase the silence timeout - Set

end_call_after_silence_ms

to a higher value (the documentation shows it can go up to the maximum call duration) . 2. Adjust reminder settings - Configure

reminder_trigger_ms

and

reminder_max_count

to control how often the agent reminds the user when they're silent. You could set

reminder_max_count

to 0 to disable reminders entirely if you want the agent to stay completely silent. [(1) ]() [(2) ]() [(3) ]() 3. Set maximum call duration - Use

max_call_duration_ms

to ensure the call doesn't exceed your desired timeframe. The default is 3,600,000 ms (1 hour) , with a maximum of 7,200,000 ms (2 hours) . [(1) ]() [(2) ]() Here's how these settings would look in your agent configuration:

json
{
  "end_call_after_silence_ms": 1800000,
  "reminder_trigger_ms": 60000,
  "reminder_max_count": 0,
  "max_call_duration_ms": 3600000
}

[(2) ]() This configuration would allow up to 30 minutes of silence before ending the call, with no reminders interrupting the user while they complete the scheduling.

​ To learn more, see the sources I considered: [[1] List Voice Agents](https://docs.retellai.com/api-references/list-agents) [[2] Create Voice Agent](https://docs.retellai.com/api-references/create-agent) [[3] Step 1: Configure global settings](https://docs.retellai.com/build/conversation-flow/global-setting) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.

### Answer You can control this behavior through your agent's prompt instructions. The key is to explicitly instruct the AI when NOT to ask follow-up questions or prompt for responses. [(1) ]() In your prompt, you should include specific instructions like: - Define clear scenarios where the agent should remain silent and wait (e.g., "After sharing the scheduling link, wait silently for the user to complete the process") - Specify that the agent should only speak if the user asks a question or requests help - Instruct the agent to avoid asking unnecessary follow-up questions during the scheduling process The Responsiveness setting also affects this behavior - it controls how responsive the agent is overall. [(2) ]() Setting it lower makes the agent respond slower and wait longer before speaking. Reducing responsiveness by 0.1 adds 0.5 seconds of agent wait time. Additionally, the Interruption Sensitivity setting determines how easily the agent gets interrupted. Setting it lower makes the agent more resilient to background speech, which could help if you want the agent to be less reactive during the scheduling process. For your specific use case, I recommend: 1. Craft explicit prompt instructions telling the agent to stay silent after sharing the link unless the user initiates conversation 2. Adjust the Responsiveness setting to make the agent less eager to fill silence 3. Set

reminder_max_count

to 0 to prevent periodic check-ins The agent's behavior is primarily driven by your prompt instructions, so being very explicit about when to speak and when to wait is crucial. [(1) ]()

​ To learn more, see the sources I considered: [[1] Prompt Engineering Guide](https://docs.retellai.com/build/prompt-engineering-guide) [[2] Step 1: Configure global settings](https://docs.retellai.com/build/conversation-flow/global-setting) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.

### Answer You can use the

NO_RESPONSE_NEEDED

feature to handle this exact scenario. When you want the AI to stay completely silent (not respond to self-talk like "alright let's see") , you need to instruct it to output exactly

NO_RESPONSE_NEEDED

in your prompt. [(1) ]() The key is being very explicit in your prompt instructions. Here's what you should include:

## Silence Rules
- If the user says "hold on", "give me a second", "wait", "alright let's see", "hmm", "let me check", or similar self-talk phrases, respond with ONLY this exact text with nothing before or after: NO_RESPONSE_NEEDED
- If you detect the user is still thinking, pausing, or not ready to respond, output ONLY: NO_RESPONSE_NEEDED
- When you output NO_RESPONSE_NEEDED, do not add ANY other text, punctuation, or explanation before or after it.
- NO_RESPONSE_NEEDED must be the complete and only content of your response.

This tells the agent to recognize self-talk and remain silent instead of responding with acknowledgments like "take your time." Additionally, you should adjust the Interruption Sensitivity setting to make the agent less reactive to these kinds of utterances. Setting it lower (around 0.5 or below) makes the agent more resilient to background speech and user interruptions, which helps prevent it from jumping in during self-talk. [(2) ]() [(3) ]() [(4) ]() The combination of explicit

NO_RESPONSE_NEEDED

instructions in your prompt and lower interruption sensitivity should significantly reduce unwanted responses during the scheduling process.

​ To learn more, see the sources I considered: [[1] no_response_needed](https://discord.com/channels/1186424376300679209/1433483896179261480) [[2] Step 2: Configure the basic settings](https://docs.retellai.com/build/single-multi-prompt/configure-basic-settings) [[3] Step 1: Configure global settings](https://docs.retellai.com/build/conversation-flow/global-setting) [[4] Handle background speech & noise](https://docs.retellai.com/build/handle-background-noise) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.