Customers can interact with AI agents in their preferred language across various digital and voice channels. Webex AI Agent Studio supports multiple languages, allowing the AI agents to understand customer input and respond in the same language.

You can create and configure an AI agent in the desired language and voice and make one as default, based on the requirements.

Webex AI Agent Studio supports Polymatch and Language Encoder multilingual models for training scripted AI agents. These models are available as part of the Swiftmatch AI engine's settings.

• For an AI agent trained using Polymatch, a distinct model is created for each language and added to the AI agent. The AI engine performs inference based on the language of the customer query.

• The Language Encoder model performs best for training data on long utterances, while Polymatch does the same for short utterances.

• The languages supported by Polymatch and the Language Encoder differ. For more information, refer to the following table.

The accuracy of an AI agent trained with Swiftmatch and mindmeld models depends on various features that are involved in the training of the AI agent and the inference of incoming user messages. The key features that decide whether a language is supported, and its accuracy are:

• Text (support for the language and the script it’s written in)

• Contextual spellcheck (if spelling mistakes in the data or user query can be corrected)

• Wordforms (handling various forms and synonyms for words present in training data)