Send to speech recognition

This endpoint retroactively sends existing calls that have not yet been transcribed to the speech recognition service. You provide arrays of call IDs, campaign lead IDs, or lead IDs along with optional parameters like languages, minimum duration, and recording side (lead, agent, or both). The service then processes these calls for transcription and returns a JSON response detailing the completed calls that were sent for transcription.

Request Body

  • call_ids (array) - An array of call IDs.
  • token (string) - The token for authentication.
  • languages (array) - An array of languages.
  • min_duration (interger) - The minimum duration for the recording.
  • recording_side (string) - The side of the recording. caller, callee, both.

The response is a JSON object with nested properties. It includes details of completed calls for the specified leads and campaign leads.

**Important: The token used to create the speech transcription for a call will be the only token authorized to retrieve the speech recognition results.

Language
Credentials
Basic
base64
:
URL
Click Try It! to start a request and see the response here!