Speech and text analytics


The following permissions are required to work with speech and text analytics features:

  • Speech and Text Analytics > Settings > All
  • Routing > Transcription Settings > All 

    Speech and text analytics is a set of features that provide automated speech and text analytics capabilities on 100% of interactions to provide deep insight into customer-agent conversations.

    From the speech and text analytics page, you can enable voice transcription, select a default program, and determine the dialects that should be analyzed in digital interactions.

    The voice transcription feature transcribes voice interactions (for example, Automatic Call Distribution (ACD) calls) in the contact center into written words that are stored as speaker separated conversational text. For more information, see About voice transcription.

    A program is a set of instructions that tell speech and text analytics what to recognize in recorded conversations between contact center participants and customers, in relation to a specific business issue. For more information, see About programs, topics, and phrases.

    Selecting a dialect for digital interactions ensures that the system applies the correct analysis.

    1. Click Admin.
    2. Under Quality, click Speech and Text Analytics.
    3. Select the Settings tab.
    4. Under Voice Transcription, select Enabled based on Queue configuration or Flow action.
    5. Under Transcript Confidence Filter, set the minimum confidence threshold required for a word to be displayed in a transcript. The default value for Word Confidence is set to 40.
    6. Turn on Transcript Content Search if you want all voice transcripts and digital interaction content for the last 35 days to be searchable. 
    7. Click Save.
    8. Complete the remaining steps in Configure voice transcription.

    1. Click Admin.
    2. Under Quality, click Speech and Text Analytics.
    3. Select the Settings tab.
    4. Under Default Program, select the fallback program to use for topic detection if no program is mapped to a Queue or Flow.
    5. Complete the remaining steps in Work with a program.

    1. Click Admin.
    2. Under Quality, click Speech and Text Analytics.
    3. Select the Settings tab.
    4. Under Expected Dialects (Language) in Digital Interactions, select one or more dialects (up to 3).


    • It is recommended that one dialect be selected to ensure the system applies the correct analysis. If multiple dialects are selected, a generic analysis will be performed unless the correct language is set in the Architect Flow for the interaction.
    • After selecting one or more dialects and saving your selections, the changes do not take effect immediately. It can take up to 15 minutes for the system to be updated.
    • If expected dialects are not selected, sentiment analysis will not function for digital interactions. 

    Out-of-the-box topics are a good way to start the topic creation process, but since they are a product of similar organizations and not specifically your organization, it is highly recommended that you modify these topics to your own specific language and terminology when working with customers or referring to products and services. For more information, see Out-of-the-box topics.
    1. Click Admin.
    2. Under Quality, click Speech and text analytics.
    3. Select the Actions tab.
    4. From the Select dialect… list, select the dialect that best represents your interactions.
    5. From the Add new topics only list, select one of the following options:
      • Add new topics only – enables you to add one or more topics to the topic list.
      • Merag topics and phrases – enables you to merge new topics with existing topics that have the same name and selected dialect.
    6. Click Generate, to generate the new out-of-the-box topics.