Manage Continuous Stream Transcription Profiles

Autorisations requises : Automatisation & IA > Lancer Automatisation & IA Studio Script Voir, Créer/Modifier

Continuous Stream Transcription provides transcription of conversation audio. It sends the transcription as a continuous stream throughout the interaction.

Add a Continuous Stream Transcription Profile

A transcription profile defines the transcription options you want to use, including the language to transcribe.

  1. Dans CXone, cliquez sur le sélecteur d'application et sélectionnezOther > Automation & AI > Transcription Hub > Continuous Stream.
  2. Click Add Transcription Profile.
  3. Enter a Transcription Profile Name. To differentiate this profile from your other profiles, use a name that highlights what makes this profile different. For example, you could name the profile for its intended use, the provider, or the language of the profile.
  4. Under Select Provider, click the transcription provider to use. You can choose from Google Transcription or CXone Transcription.
  5. Click Next.

  6. On the Configuration page, complete the fields to define the transcription options for this profile.

    Field Details
    Transcription Type

    Choose the Google Transcription account to use with this profile:

    • Select CXone to use the account owned by NICE CXone.
    • Select Your Account to use your organization's account.

    JSON Service Account

    The service account key for the Google Transcription account you're using:

    • If you're using the NICE CXone account, use the key provided for you by your Représentant de compte CXone.
    • If you're using your own account, use the key file you created and downloaded from your Google Cloud Console.

    Copy and paste the entire contents of the key file into this field, including the curly braces surrounding the key.

    The service account key is a JSON object similar to the following example:

    {

    "type": "service_account",
    "project_id": "ic-demo2-aai-gcp",
    "private_key_id": "sdv80sdf08ssd9sdf0sdf8sdfsdf90sdf8",
    "private_key": "-----BEGIN PRIVATE KEY-----
    nMIIEvgIBADANBgkqhkiG9w0BAQEFAASCBKgwggSkAgEAAoIBAQCzgrS8vp
    <private key has been truncated for this example>
    ----END PRIVATE KEY-----\n",
    "client_email": "your@client_email-gcp.iam.gserviceaccount.com",
    "client_id": "123456789",
    "auth_uri": "https://accounts.google.com/o/oauth2/auth",
    "token_uri": "https://oauth2.googleapis.com/token",
    "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
    "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/dialogflow-dthjop%40ic-demo2-aai-gcp.iam.gserviceaccount.com"
    }
    Language Code Select the language that you want this profile to transcribe.
    Model

    Sélectionnez le modèle de machine learning devant être utilisé par le service de transcription pour les données audio. Ces modèles ont été entraînés pour reconnaître la parole à partir de certains types et sources d’éléments audio. Certaines langues ne prennent pas tous les modèles. Reportez-vous à la documentation de Google pour plus d'informations sur la prise en charge.

    Les options disponibles sont :

    • Commande et recherche : utilisez cette option lors de la transcription de brefs clips audio, comme des commandes ou des recherches vocales. Envisagez d’utiliser Dernier court à la place.
    • Par défaut : utilisez cette option lorsque l’audio ne correspond pas aux autres modèles. Elle permet de transcrire tout type d’élément audio, mais les résultats peuvent se révéler de moindre qualité dans certains cas.
    • Dernier long : utilisez cette option pour les contenus de forme longue, comme un discours spontané ou des conversations.
    • Dernier court : utilisez cette option pour les énoncés qui ne durent que quelques secondes, par exemple les commandes. Envisagez d’utiliser ce modèle à la place de Commande et recherche.
    • Appel téléphonique : utilisez cette option pour la transcription d’un appel téléphonique.
    Use Enhanced

    Select this option to use the enhanced version of your selected Model. This is only an option if you are using the Phone Call model. This can help increase the accuracy of transcription.

    The default is for this option to be disabled. Enabling this option increases the cost of transcription.
    Interim Results Select this option if you want the transcript to show temporary results that are refined over time. The default is for this option to be disabled. For SalesForce Assist, do not enable this option. It requires the final utterance results.For Copilot for Agents, do not enable this option. It requires the final utterance results.
    Field Details
    Language Code Select the language that you want this profile to transcribe. Currently the only available language is English.
    Enable Automatic Punctuation

    Click to enable this option if you want CXone Transcription to add punctuation marks such as commas and question marks to the transcription results.

    The default is for this option to be disabled.

    Interim Results Click to enable this option if you want the transcript to show temporary results that are refined over time. The default is for this option to be disabled.
  7. Click Add.