Language Profiles

Customer experience functionalities such as live translation, transcription and others rely on the system's ability to handle multiple languages in a business workflow.

Language specific services involve two participant roles in a conversation: a customer and an agent, potentially being fluent in different languages. We offer dedicated language profiles for each, therefore a Language Profile designates a language for the customer or the agent as well as the speech-to-text and text-to-speech providers and voice models where available. It also specifies what use cases or language services the profile can be used for (e.g. translation) as well as business specific key phrase vocabularies and the ability to correct translation errors by text manipulation.

Create agent language profile

  1. Navigate to AI Administration > Language Profiles on the portal.

  2. Click the Agent tab and Create an agent language profile.

  3. Enter the Language profile name, select a Language from the list, then click Next.

  4. Select the feature you would like this profile to be used for.

  5. For the Call Translation and Voice Bot features:

    1. Select the Speech to text provider

    2. When available for the selected STT provider, select a key phrase Vocabulary.

    3. When available, select a Text manipulation ruleset.

    4. Select a Text to speech provider from the list. If offered, designate the Speech to text voice model too.

      Note that the voice models compatible with the selected language are placed at the top of the list, marked by a star. While you can select other items, those might not work with the selected language and providers.

    5. When available for the TTS provider, click the Advanced TTS options (pencil icon) to configure:

      1. Enable the Read number digit by digit option to have multi digit numbers uttered in a digit by digit manner with a desired speed. This is useful for identification-like values, where a multi-digit string should not be uttered like one big number.

  6. Click Create. The new profile is saved and its details show up next to the list.

  7. Click the Translations tab on the details panel to see and modify the translation specific details between this agent profile and all the available customer profiles.

  8. Click the Translation Engine dropdown for any of the customer profile you would explicitly like to select a specific engine for. The default is Microsoft Azure.

Create customer language profile

  1. Navigate to AI Administration > Language Profiles on the portal.

  2. Click the Customer tab and Create a customer language profile.

  3. Enter the Language profile name, select a Language from the list, then click Next.

  4. Select the feature you would like this profile to be used for.

  5. For the Call Translation and Voice Bot features:

    1. Select the Speech to text provider

    2. When available for the selected STT provider, select a key phrase Vocabulary.

    3. When available, select a Text manipulation ruleset.

  6. For the Call Translation, Voice Bot and Workflow TTS features:

    1. Select a Text to speech provider from the list. If offered, designate the Speech to text voice model too.

      Note that the voice models compatible with the selected language are placed at the top of the list, marked by a star. While you can select other items, those might not work with the selected language and providers.

    2. When available for the TTS provider, click the Advanced TTS options (pencil icon):

      1. Enable the Read number digit by digit option to have multi digit numbers uttered in a digit by digit manner with a desired speed. This is useful for identification-like values, where a multi-digit string should not be uttered like one big number.

  7. For the Recording Transcription feature, select an Offline Transcription Provider from the list.

  8. Select the Voice Bot feature to let voice conversational bots use this profile when instructed by the Customer Language Profile workflow node.

  9. Select the Workflow TTS feature to let TTS-using voice workflows use this profile to utter their TTS text.

Note

Note that multiple features might require the same service—e.g. both Call Translation and Workflow TTS requires the TTS service—however not all might allow the same set of providers. The list of providers will be filtered to serve all the features selected.

Delete a language profile

  1. Navigate to AI Administration > Language Profiles on the portal.

  2. Click the tab for the designated language profile type (Agent or Customer).

  3. Find and click the language profile you would like to remove.

  4. Click Delete at the top, and confirm your intent.

Note

The item will be removed even if it is being referenced by other configurations. Make sure it is not in use by an important business entity.

Create key phrase vocabularies

Modern translation services rely on AI models for extremely fast and high quality results. However, being reliant on generic text and speech data, the result could contain less precise or inadequate phrases for the particular business context. The vocabulary of key phrases aids the language services in using precise phrases.

  1. While at the Language Profiles menu, click the Vocabulary tab to see their list.

  2. Click Create and type a name for the new vocabulary.

  3. Type a phrase in the Add a new phrase field and click Add to insert phrases individually.

  4. Click Import to upload a list of phrases from a CSV or text file in one operation and decide whether duplicates found will be replaced or appended.

  5. Click Create to create the new vocabulary.

  6. Select an Agent or Customer profile, and select from the Speech To Text Provider Vocabulary dropdown.

Delete a key phrase vocabulary

  1. Navigate to AI Administration > Language Profiles on the portal and click Vocabulary.

  2. Click the desired item and click Delete on the details panel.

  3. Confirm your intent.

Create text manipulations

For translation services involving STT/TTS workflows the system offers the ability to address typical mistranslations of business specific identifiers and other tokens using powerful regex statements, including capture groups.

For example, if the input string is Inc 1234 but the expected outcome is INC1234 (a business token, e.g. an ID), then your Regex field should be: Inc\s(\d{4}) while the Replace field should be INC$1.

Such manipulations are executed on the chunk of text the STT engine generated from the last utterance of the relevant party, and before the text is translated to the target language and handed off to the TTS engine.

  1. While at the Language Profiles menu, click the Text Manipulations tab to see the list.

  2. Click Create and type a name for the new text manipulation ruleset.

  3. Type a Regex to match a specific word or phrase in the text generated by the STT provider. Also type a Replacement word or phrase and an optional Description for this rule.

    When typing the regex and replacements, mind the language this text manipulation ruleset is expected to be used with, and apply language specific writing notations when relevant. Do not use accented characters as those are not necessarily available or translated precisely by the translation services. As usual with AI enforced features, proper testing and experimentation is due before you roll any config into production.

  4. Click Add to insert the rule into the ruleset list.

  5. Repeat these steps to add all rules to the ruleset and then click Create to save the new text manipulation ruleset.

  6. Edit or create the corresponding agent and/or customer language profile and select this ruleset in the Text Manipulation List dropdown, then create or save the profile.

Delete text manipulations

  1. While at the Language Profiles menu, click the Text Manipulations tab to see the list.

  2. Click the desired item and click Delete on the details panel.

  3. Confirm your intent.