Skip to main content
It’s quite common to want to use different agents under the same number, and quite common to provide context based on caller for a call. For outbound calls, you can do that simply by supplying the call specific information when you call the create phone call API. For inbound calls however, you are not the one initiating the call, and you need a way to notify you when that inbound call is received and you can then process it. This inbound call webhook is designed for this purpose. Once setup, you can override agent id, set dynamic variables and other fields specific to that call, and then you can process the call accordingly. It is part of your number configuration, and it works for numbers that you have purchased or imported. This feature does not apply for dial to sip calls calls, as you can provide call specific information when you register the phone call.

​
Webhook Spec

The webhook will POST the payload to your endpoint. The webhook has a timeout of 10 seconds. If within 10 seconds no success status (2xx) is received, the webhook will be retried, up to 3 times. The webhook can be verified using your Retell API Key to make sure it comes from Retell AI. Read more at Secure the webhook.

​
Request payload

These fields might be provided in the payload depending on your configuration:
  • agent_id: if the number has inbound agent id set, you will see it in payload
  • from_number: this will always show up in payload, helps you identify the caller and process the call accordingly
  • to_number: this will always show up in payload, helps you identify the receiver and process the call accordingly
Note that the call is not connected, and a call object is not yet created (and if you decided not to take the call for example, the call object will not be created). Therefore you will not have a call object and call id inside the payload. Here’s a sample payload: 
{
  "event": "call_inbound",
  "call_inbound": {
    "agent_id": "agent_12345",
    "from_number": "+12137771234",
    "to_number": "+12137771235"
  }
}

​
Response

We expect a JSON response with a successful status code (2xx) with fields grouped under call_inbound. Here’re the allowed fields (all of them are optional):
  • override_agent_id: if you want to override the agent id, you can set it here
  • override_agent_version: if you want to override the agent version, you can set it here
  • dynamic_variables: if you want to set dynamic variables for this inbound call, you can set it here
  • metadata: if you want to set metadata for this inbound call, you can set it here
  • agent_override: if you want to override the agent settings.

​
Agent Override

You can also override per‑call agent behavior without modifying the saved agent by returning an agent_override object. The override is applied only for this call. Supported groups:
  • agent: Partial Agent settings (voice agents). Useful fields include voice_id, voice_model, fallback_voice_ids, voice_temperature, voice_speed, volume, language, normalize_for_speech, pronunciation_dictionary, boosted_keywords, stt_mode, vocab_specialization, denoising_mode, responsiveness, interruption_sensitivity, enable_backchannel, backchannel_frequency, backchannel_words, end_call_after_silence_ms, max_call_duration_ms, begin_message_delay_ms, ring_duration_ms, reminder_trigger_ms, reminder_max_count, ambient_sound, ambient_sound_volume, allow_user_dtmf, user_dtmf_options, voicemail_option, webhook_url, webhook_timeout_ms, data_storage_setting, opt_in_signed_url, pii_config, post_call_analysis_data, post_call_analysis_model.
  • retell_llm: Partial Retell LLM settings. Supported keys include model, s2s_model, model_temperature, knowledge_base_ids, kb_config, start_speaker, begin_after_user_silence_ms, begin_message.
  • conversation_flow: Partial Conversation Flow settings. Supported keys include model_choice, model_temperature, knowledge_base_ids, kb_config, start_speaker, begin_after_user_silence_ms, begin_message.
Notes:
  • If both override_agent_id/override_agent_version and agent_override are provided, we first resolve the target agent by id/version, then apply agent_override on top for this call.
  • Overrides must satisfy the same validation rules as agent creation (e.g. voice/language compatibility, value ranges). Invalid overrides may cause the call to be rejected.
  • Overrides do not persist back to the saved agent.
Here’s a sample response: 
{
  "call_inbound": {
    "override_agent_id": "agent_12345",
    "override_agent_version": 1,
    "agent_override": {
      "agent": {
        "voice_id": "11labs-Adrian",
        "voice_temperature": 0.6,
        "interruption_sensitivity": 0.8,
        "max_call_duration_ms": 1800000
      },
      "retell_llm": {
        "model": "gpt-4o-mini",
        "model_temperature": 0.2,
        "knowledge_base_ids": ["kb_abc123"],
        "start_speaker": "agent",
        "begin_message": "Hi {{customer_name}}, thanks for calling."
      }
    },
    "dynamic_variables": {
        "customer_name": "John Doe"
    },
    "metadata": {
        "random_id": "12345"
    }
  }
}

​
FAQ

The call would continue to stay in ringing state.
It would get retried up to 3 times. If all of those attempts fail, it will check whether this number has an inbound agent id set. If it does, it will then try to connect the call to that agent. If not, it will then disconnect the call.
Yes, you can. To selectively reject some inbound calls:
  • Unset the Inbound Call Agent in the phone number setting
  • Enable the Inbound Webhook
  • Listen to webhook request body call_inbound.from_number
    • If you want to pick up the call, respond with a 200 status code containing the “call_inbound.override_agent_id” as a JSON object.
    • If you want to reject the call, respond with a 200 status code without containing the “call_inbound.override_agent_id” as a JSON object.