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

# input_audio.speech_started

Emitted when the service detects user speech on the input audio stream. This can arrive before any transcription text is available.

## Event fields

<ResponseField name="event_id" type="string" required>
  Unique id for this server event.
</ResponseField>

<ResponseField name="type" type="string" required>
  Event type. Must be `input_audio.speech_started`.
</ResponseField>

<ResponseField name="item_id" type="string" required>
  Provisional user audio item id used to correlate later transcription events and the created conversation item.
</ResponseField>

<ResponseField name="audio_start_ms" type="integer" required>
  Speech start time in milliseconds on the session input-audio timeline.
</ResponseField>

<ResponseExample>
  ```json input_audio.speech_started theme={null}
  {
    "event_id": "evt_input_audio_speech_started_001",
    "type": "input_audio.speech_started",
    "item_id": "item_audio_001",
    "audio_start_ms": 1200
  }
  ```
</ResponseExample>