[CRITICAL] Inbound calls have dead air due to LLM timeout(Failed to get response from any LLM provider – Operation timed out )

Support Help
1

We are facing a critical issue with inbound calls where the AI agent either does not speak at all or starts speaking very late. This is happening too often.

Our agent is configured as “AI speaks first” using a dynamic opening message, but in multiple calls users hear silence and the call eventually drops.

From our logs we consistently see this pattern:

Inbound webhook triggered  
Dynamic variables received  
Call started  
(5–6 seconds delay)  
LLM error: Failed to get response from any LLM provider – Operation timed out  
Call ends

So the call connects successfully and dynamic data is passed correctly, but the AI fails to generate the first response in time, resulting in dead air for the caller.

This is happening on live customer calls and is blocking us from using inbound calling in production.

Has anyone else faced this?
Is there a recommended way to handle LLM timeouts, or pre-generation of the opening message so calls never start with silence?

Thanks,
Ayush

2

I don’t have specific information about troubleshooting LLM timeout errors during inbound call initialization in the available sources. However, I can point you to relevant configuration options that may help.

Relevant Configuration Options:

You can configure begin_message_delay_ms in your agent settings, which controls the delay before the agent starts speaking(1). The default is 1000ms(1).

const agentResponse = await client.agent.create({
  begin_message_delay_ms: 1000,
  // other settings
});

(1)

For inbound calls specifically, you can use the inbound webhook to override agent settings per call(2). The webhook allows you to return an agent_override object that can modify behavior for that specific session(2):

{
  "call_inbound": {
    "agent_override": {
      "retell_llm": {
        "begin_message": "Hi {{customer_name}}, thanks for calling."
      }
    },
    "dynamic_variables": {
      "customer_name": "John Doe"
    }
  }
}

(2)

What I’d Recommend:

Since your logs show “Failed to get response from any LLM provider – Operation timed out,” this suggests the LLM is timing out during response generation. You might want to:

  1. Check if you have fallback voice/LLM providers configured(1)
  2. Verify your webhook_timeout_ms setting (default is 10000ms)(1)
  3. Consider using a faster LLM model if available

For direct support with this production-critical issue:

3

  • we need dynamic message at the start so we cannot use begin_message.

  • we don’t have voice fallback but there is no option to add llm provider fallback

  • we are using retell dashboard for managing the agent

    2026-02-01 19:12:11.159 call_67629d751ab4f8170e8edbd67d3 info: Starting call: call_67629d751ab4f8170e8edbd67d3

    2026-02-01 19:12:12.804 call_67629d751ab4f8170e8edbd67d3 info: Webhook triggered for call_started

    2026-02-01 19:12:13.144 call_67629d751ab4f8170e8edbd67d3 info: Webhook response received for call_started

    2026-02-01 19:12:23.308 call_67629d751ab4f8170e8edbd67d3 error: Error encountered in LLM call: Failed to get response from any LLM provider: Operation timed out

    2026-02-01 19:12:27.804 call_67629d751ab4f8170e8edbd67d3 info: Ending call: call_67629d751ab4f8170e8edbd67d3

    2026-02-01 19:12:28.966 call_67629d751ab4f8170e8edbd67d3 info: Webhook triggered for call_ended

    2026-02-01 19:12:28.966 call_67629d751ab4f8170e8edbd67d3 info: Webhook triggered for call_analyzed

    2026-02-01 19:12:29.307 call_67629d751ab4f8170e8edbd67d3 info: Webhook response received for call_analyzed

    2026-02-01 19:12:29.314 call_67629d751ab4f8170e8edbd67d3 info: Webhook response received for call_ended

As you can see the logs the webook response are working fine, the llm provider is failing due to time out

4

Hello @ayush

I see you have a 75k tokens call, which is way above the limit of 32k tokens per call.