​ To learn more, see the sources I considered: [[1] Update Conversation Flow](https://docs.retellai.com/api-references/update-conversation-flow) [[2] List Retell LLMs](https://docs.retellai.com/api-references/list-retell-llms) [[3] Get Retell LLM](https://docs.retellai.com/api-references/get-retell-llm) [[4] Step 2: Configure the basic settings](https://docs.retellai.com/build/single-multi-prompt/configure-basic-settings) [[5] Step 1: Configure global settings](https://docs.retellai.com/build/conversation-flow/global-setting) [[6] Agent not waiting in between statements/questions despite pauses in prompt](https://discord.com/channels/1186424376300679209/1409973649221619812) ​

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

### Answer You have a few options to control how long the agent waits for a user response: 1.

begin_after_user_silence_ms

parameter If the agent is configured to wait for the user to speak first, you can set

begin_after_user_silence_ms

to specify how long (in milliseconds) the AI will wait before beginning the conversation. [(1) ]() [(2) ]() [(3) ]() Example:

json
"begin_after_user_silence_ms": 2000

[(1) ]() This means the agent will wait 2000ms (2 seconds) for the user before starting. If not set, the agent will wait indefinitely for the user to speak. [(1) ]() [(2) ]() [(3) ]() 2. Responsiveness setting You can adjust the Responsiveness setting in Speech Settings. Reducing responsiveness by 0.1 adds 0.5 seconds of agent wait time. [(4) ]() [(5) ]() 3. Reminder frequency Configure how often the agent will remind the user when the user is inactive. 4. Prompt-based approach Structure your prompts with explicit "wait for user response" instructions between questions. [(6) ]() Example format:

1. Ask for user's name.
wait for user response

2. Ask if user needs a refund...
wait for user response

### Answer You can adjust reminder frequency in the Speech Settings section. [(1) ]() , [(2) ]() There are two key parameters: -

reminder_trigger_ms

– Sets how long (in milliseconds) the agent waits after speaking before sending a reminder if the user is silent. Default is 10000 ms (10 seconds) . [(3) ]() , [(4) ]() , [(5) ]() -

reminder_max_count

– Controls how many times the agent will remind the user when unresponsive. Default is 1. Set to 0 to disable reminders. [(3) ]() , [(4) ]() , [(5) ]() In the Dashboard: Go to Speech Settings → Reminder Message Frequency to configure these values. [(2) ]() Via API: You can set these when updating a voice agent:

json
"reminder_trigger_ms": 10000,
"reminder_max_count": 2

[(3) ]()

​ To learn more, see the sources I considered: [[1] Step 1: Configure global settings](https://docs.retellai.com/build/conversation-flow/global-setting) [[2] Discord message from @nav_347 on 2025-03-14](https://discord.com/channels/1186424376300679209/1294891368505937952/1350121491865407642) [[3] Update Voice Agent](https://docs.retellai.com/api-references/update-agent) [[4] List Voice Agents](https://docs.retellai.com/api-references/list-agents) [[5] Get Agent Versions](https://docs.retellai.com/api-references/get-agent-versions) ​

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