Get Bot Transcript

Returns transcript of the conversation between a virtual agent and a contact. This action can also return the conversation's intent information. The exact data that's captured depends on the configuration setting selected on the Transcript page of the virtual agent app in Virtual Agent Hub. You can capture the transcript only, the intent only, the transcript and the intent, or nothing. The captured data is stored in a variable. You can use the stored data in any way you want, but you must configure the script to manage it. For example, for interactions that are transferred to human agents, you could pass the transcript to the agent application using a Runapp action. Use Get Bot Transcript with supported virtual agents. See the Dependencies section on this page for more information.

Dependencies

• Get Bot Transcript supports the following virtual agent providers:

  • Amazon Lex V1 (voice and chat)
  • Amazon Lex V2 (voice and chat)
  • Cognigy  (chat only)
  • CXone CXone SmartAssist Powered by Amelia (chat only)
  • Google Dialogflow ES (voice and chat)
  • Google Dialogflow CX (voice and chat)
  • IBM Watson (chat only)
  • Microsoft Azure (voice and chat)
  • Nuance Mix (voice and chat)
  • Omilia (chat only)
  • Salesforce Einstein (chat only)
  • Custom virtual agent integrations (voice and chat)
• This action is not supported for use with voice virtual agent integrations that use SIP Protocol used for signaling and controlling multimedia communication sessions such as voice and video calls. backchannel connections.
• The Transcript option must be enabled on the Transcript page in the configuration app in Virtual Agent Hub for the virtual agent you want to use this action with.
• Captured data is stored temporarily for the life of the contact ID. If you need to save the data, you must configure the script to send it to an archive.
• You can use Get Bot Transcript with all virtual agent Studio actions: Textbot Exchange, Voicebot Exchange, and Voicebot Conversation.

Supported Script Types

Chat	Phone	Digital

Input Properties

These properties define data that the action uses when executing.

Property	Description
Add Caption	Enter a short phrase that uniquely identifies this action in the script. The caption appears on the script canvas under the action icon.
Format	Enter the format you want the transcript to be returned in. Supported formats are HTML and JSON.

Output Properties

These properties contain variables that hold data returned from executing the action. They're available for reference and use when the action completes.

Property	Description
TranscriptVarName (out)	Contains the transcribed text.

Result Branch Conditions

Result branch conditions allow you to create branches in your script to handle different outcomes when an action executes.

Condition	Description
Default	Path taken unless the script meets a condition that requires it to take one of the other branches. It is also taken if the action's other branches are not defined.
Error	The path taken when the action doesn't execute properly. For example, when there's an unexpected problem, such as poor connectivity, syntax errors, HTTP error codes, and so on. The ERR variable should be populated with a condensed explanation of the problem.
Success	Path taken if the action completes without errors and any API calls or data returns were successful (2xx response codes).

Required SNIPPET Action Code

This action requires the Transcript snippet code. This code creates a dynamic object to hold the transcript data. It also copies the transcript content from the object to a variable so it can be passed to the agent application.

Example Script

The example script shows a virtual agent script that uses the Voicebot Exchange action. It includes a branch for when the virtual agent signals that the interaction needs to be transferred to a human agent. That branch is shown in the image below.

When the human agent answers the call, the Get Bot Transcript action requests the transcript and passes the returned data to the Snippet action. The snippet code creates a dynamic data object called myTranscript. It then converts the data into JSON and stores it in a variable called transcriptHtml. This allows it to be sent to the agent application. The Runapp action is configured to display a web page that contains the transcript.

Download script.