Language switching

Overview

End users can switch the conversation language in the following ways, depending on the channel:

  • Autodetect (Chat and Email only): If an end user sends a message with at least three meaningful words and 20 characters in an enabled language, your AI Agent attempts to detect and switch to that language. Common words like “and” or “the” do not count toward the three-word minimum.

  • Language name (Chat only): If an end user types the exact name of an enabled language (e.g., “French” or “Français”), your AI Agent switches to that language. This only works with exact matches—typos or phrases like “Do you speak French?” do not trigger a change.

  • Chat settings (Chat only): In Ada’s web chat, end users can click the Settings icon, then select Change language to pick from the languages you have enabled in your AI Agent.

For information about how language switching works in Voice, see Enable Voice in multiple languages.

Limitations

Language switching has the following constraints. Language detection depends on various factors, and switching may not happen as expected in some situations.

  • Minimum character and word requirements for Latin-based languages

    • For messages written entirely in Latin characters, the message must contain at least 3 words (space-separated) and 20 characters to trigger a language switch
    • This requirement applies to all languages except: Greek, Hindi, Japanese, Khmer, Korean, Myanmar, Punjabi, Tamil, Thai, Simplified Chinese, and Traditional Chinese
  • Switch-disabled language pairs

    • Some languages are considered too similar by the detection model, so switching between them is disabled to prevent premature language changes
    • These pairs include:
      • Malay and Indonesian
      • Simplified Chinese and Traditional Chinese
      • Spanish and Catalan
      • Croatian and Serbian
  • Switch-disabled languages

    • Once set to these languages, the AI Agent cannot switch out of them through language detection:
      • Haitian Creole
      • Tagalog
      • Bosnian
  • Non-Latin writing systems

    • For languages with non-Latin writing systems (like Hindi, Chinese, etc.), Ada does not support recognizing Latin-based versions of these languages
    • For example, Hindi written in Latin characters (like “kya hal-chal hai”) cannot be detected, while the same phrase in Devanagari script (क्या हाल-चाल है) can be recognized
  • Diacritics requirement

    • For languages that use diacritics (like Vietnamese), the model requires proper diacritic usage
    • Messages without diacritics may be misidentified (e.g., “voi” without diacritics might be detected as Italian instead of Vietnamese)
  • Unsupported languages

    • The language detection model cannot detect these languages:
      • Afrikaans
      • Albanian
      • Bosnian
      • Catalan
      • Chichewa (Nyanja)
      • Kazakh
      • Kinyarwanda
      • Macedonian
      • Ndebele (South)
      • Serbian
      • Sesotho
      • Shona
      • Swahili
      • Xhosa
      • Zulu
  • Unicode-based detection

    • For certain languages with unique writing systems, detection is based on Unicode rather than the model
    • This applies when the entire message uses only one of these writing systems:
      • Greek
      • Devanagari
      • Hiragana
      • Katakana
      • Khmer
      • Hangul
      • Myanmar
      • Gurmukhi
      • Tamil
      • Thai
  • Denied words

    • Messages containing certain common words across multiple languages will not trigger a switch
    • These words include: “no”, “meta”, “variable”, “swish”, “support”, “agent”, “face”, “id”, “selfie”, “bet”, “confirmation”, “start”, “vacation”, “hold”, “nya”, “fuel”, “point”, “domain”

Use cases

Language switching enables end users to communicate in their preferred language during a conversation.

  • Support multilingual end users: Allow end users who speak multiple languages to switch to whichever language they are most comfortable with.
  • Handle mid-conversation language changes: Support end users who start in one language but need to continue in another.
  • Accommodate regional preferences: Enable end users to select a regional language variant when multiple options are available.