# action.start Start a live translation session. | Name | Type | Default | Description | |:-|:-|:|:--| | start Required | object | - | An object that contains the [start parameters](#start-parameters). | ## **start Parameters** | Name | Type | Default | Description | |:-|:-|:|:-| | webhook Optional | string | - | The webhook URI to be called. Authentication can also be set in the url in the format of username:password@url. | | lang Required | string | en | The language to transcribe.
Learn more about our supported Voices & Languages [here](/guides/voice-and-languages). | | live_events Optional | boolean | false | Whether to enable live events. | | ai_summary Optional | boolean | false | Whether to enable AI summarization. | | speech_timeout Optional | integer | 60000 | The timeout for speech recognition.
**Possible Values:** [Minimum value: 1500, Maximum Value: None] | | vad_silence_ms Optional | integer | 100 | Voice activity detection silence time in milliseconds.
**Possible Values:** [Minimum value: 1, Maximum Value: None] | | vad_thresh Optional | integer | 400 | Voice activity detection threshold.
**Possible Values:** [Minimum value: 0, Maximum Value: 1800] | | debug_level Optional | integer | 0 | Debug level for logging. | | direction Required | [] | local-caller | The direction of the call that should be transcribed.
**Possible Values:** [remote-caller, local-caller] | | summary_prompt Optional | string | - | The prompt for summarization. | ## **Example** yaml andJson live_transcribe: action: start: webhook: https://example.com/webhook lang: en live_events: true ai_summary: false speech_timeout: 30 vad_silence_ms: 500 vad_thresh: 0.6 debug_level: 2 direction: - remote-caller - local-caller speech_engine: default summary_prompt: Summarize this conversation