live_transcribe
live_transcribe
live_transcribe
Start live transcription of the call. The transcription will be sent to the specified webhook URL.
An object that accepts the following properties.
The action to perform. See actions below.
The action property controls the transcription session. Use start to begin transcribing with configuration options, stop to end an active session, or summarize to request an on-demand AI summary mid-session.
Start a live transcription session.
The URL to receive transcription events via HTTP POST.
When live_events is enabled, partial results are sent as they occur.
When ai_summary is enabled, a summary is sent when the session ends.
Authentication can also be set in the URL in the format of username:password@url.
The language to transcribe. See supported voices & languages.
Whether to enable live events.
Whether to enable automatic AI summarization. When enabled, an AI-generated summary of the conversation will be sent to your webhook when the transcription session ends.
The timeout for speech recognition in milliseconds. Minimum value: 1500.
Voice activity detection silence time in milliseconds.
Default depends on the speech engine: 300 for Deepgram, 500 for Google. Minimum value: 1.
Voice activity detection threshold. Range: 0 to 1800.
Debug level for logging.
The direction of the call that should be transcribed. Possible values: remote-caller, local-caller.
The speech recognition engine to use. Possible values: deepgram, google.
The AI prompt that instructs how to summarize the conversation when ai_summary is enabled.
This prompt is sent to an AI model to guide how it generates the summary.
Example: “Summarize the key points and action items from this conversation.”