Feature Release

This is the announcement for an upcoming ASAPP feature. Your ASAPP account team will provide a target release date and can direct you to more detailed information as needed.

Overview

ASAPP is adding an AutoTranscribe implementation pattern for Twilio. ASAPP’s Twilio Media Gateway will allow Twilio Media Streams audio to be easily sent to AutoTranscribe. The same call signaling integration via API will be leveraged as is used in the integration with the SIPREC Media Gateway. Media Gateways will support receiving Twilio Media Streams and requests to start and stop transcription.

Use and Impact

The new Media Gateway will allow for a simplified and easy integration for customers leveraging Twilio as their CCaaS provider, reducing time and effort of sending call media to ASAPP.

How It Works

Procedure of streaming audio to ASAPP:

  1. Authenticate with ASAPP to obtain an access URL.
  2. Instruct Twilio to start sending Media Streams to the ASAPP Media Gateway; the ASAPP Media Gateway will then receive real-time audio as well as Call SID data.
  3. Send start and stop requests to control when transcription occurs. Start and stop requests are used to start, pause, resume, and end conversations.
  4. Receive transcript outputs leveraging one of ASAPP’s transcription delivery mechanisms. Configuration Transcription settings (e.g. redaction, language) must be configured as part of implementing AutoTranscribe and will be reflected in the messages returned from this endpoint. No further configuration is required.

For developers, see ASAPP’s API Reference for information on interacting with the Media Gateway to retrieve an access URL, start and stop transcription.

FAQs

  1. Is integration with the Start/Stop API required? Yes. Start requests to the API provide ASAPP with required metadata (i.e. agent and customer identifiers) and indicate which audio corresponds to the agent and customer respectively. Stop requests are also required, as they allow AutoTranscribe to exclude hold and queue audio from transcription. This is a requirement for downstream services to function properly, ensuring transcription is only leveraged where necessary.
  2. How does Twilio handle audio forking? Please refer to Twilio Documentation for details on how audio forking is handled.