> ## Documentation Index
> Fetch the complete documentation index at: https://docs.outspeed.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Client Events

> These are the events that Realtime servers accept from the client

## Overview

These events are accepted by the Realtime servers via WebRTC datachannel from the client.
Each event has a specific structure and purpose for managing realtime interactions.

## `session.update`

Send this event to update the session's default configuration. The client may send this event at any time to update any field, except for voice. Note that once a session has been initialized with a particular model, it can't be changed to another model using `session.update`.

When the server receives a `session.update`, it will respond with a `session.updated` event showing the full, effective configuration. Only the fields that are present are updated. To clear a field like instructions, pass an empty string.

### Properties

<ResponseField name="event_id" type="string" optional>
  Client-generated ID used to identify this event.
</ResponseField>

<ResponseField name="type" type="string" required>
  The event type, must be `session.update`.
</ResponseField>

<ResponseField name="session" type="object" required>
  Realtime session object configuration.
</ResponseField>

<CodeBlock title="session.update Example">
  ```json theme={null}
  {
      "event_id": "event_123",
      "type": "session.update",
      "session": {
          "modalities": ["text", "audio"],
          "instructions": "You are a helpful assistant.",
          "voice": "sage",
          "input_audio_format": "pcm16",
          "output_audio_format": "pcm16",
          "input_audio_transcription": {
              "model": "whisper-1"
          },
          "turn_detection": {
              "type": "server_vad",
              "threshold": 0.5,
              "prefix_padding_ms": 300,
              "silence_duration_ms": 500,
              "create_response": true
          },
          "tools": [
              {
                  "type": "function",
                  "name": "get_weather",
                  "description": "Get the current weather...",
                  "parameters": {
                      "type": "object",
                      "properties": {
                          "location": { "type": "string" }
                      },
                      "required": ["location"]
                  }
              }
          ],
          "tool_choice": "auto",
          "temperature": 0.8,
          "max_response_output_tokens": "inf"
      }
  }
  ```
</CodeBlock>

## `conversation.item.create`

Add a new Item to the Conversation's context, including messages, function calls, and function call responses. This event can be used both to populate a "history" of the conversation and to add new items mid-stream, but has the current limitation that it cannot populate assistant audio messages.

### Properties

<ResponseField name="event_id" type="string" optional>
  Client-generated ID used to identify this event.
</ResponseField>

<ResponseField name="type" type="string" required>
  The event type, must be `conversation.item.create`.
</ResponseField>

<ResponseField name="previous_item_id" type="string" optional>
  The ID of the preceding item after which the new item will be inserted. If not set, the new item will be appended to the end of the conversation.
</ResponseField>

<ResponseField name="item" type="object" required>
  The item to add to the conversation.
</ResponseField>

<CodeBlock title="conversation.item.create Example">
  ```json theme={null}
  {
      "event_id": "event_345",
      "type": "conversation.item.create",
      "previous_item_id": null,
      "item": {
          "id": "msg_001",
          "type": "message",
          "role": "user",
          "content": [
              {
                  "type": "input_text",
                  "text": "Hello, how are you?"
              }
          ]
      }
  }
  ```
</CodeBlock>

## `response.create`

This event instructs the server to create a Response, which means triggering model inference. When in Server VAD mode, the server will create Responses automatically.

### Properties

<ResponseField name="event_id" type="string" optional>
  Client-generated ID used to identify this event.
</ResponseField>

<ResponseField name="type" type="string" required>
  The event type, must be `response.create`.
</ResponseField>

<ResponseField name="response" type="object" required>
  Create a new Realtime response with these parameters.
</ResponseField>

<CodeBlock title="response.create Example">
  ```json theme={null}
  {
      "event_id": "event_234",
      "type": "response.create",
      "response": {
          "modalities": ["text", "audio"],
          "instructions": "Please assist the user.",
          "voice": "sage",
          "output_audio_format": "pcm16",
          "tools": [
              {
                  "type": "function",
                  "name": "calculate_sum",
                  "description": "Calculates the sum of two numbers.",
                  "parameters": {
                      "type": "object",
                      "properties": {
                          "a": { "type": "number" },
                          "b": { "type": "number" }
                      },
                      "required": ["a", "b"]
                  }
              }
          ],
          "tool_choice": "auto",
          "temperature": 0.8,
          "max_output_tokens": 1024
      }
  }
  ```
</CodeBlock>