A voice agent mispronounces a technical product name. How can the developer fix this without changing the response text?
Select an answer to reveal the explanation.
Short Explanation and Infographic
Todd Lammle: 'Imagine you're building a chatbot and this exact situation comes up — use ssml tags in the response to provide correct pronunciation guidance to the tts engine is your go-to move. SSML (Speech Synthesis Markup Language) tags can be embedded in text responses to guide TTS pronunciation; stress; and pacing without altering the visible text content. This is a classic Domain 7: Multi-Modal Integration concept you'll want locked in before exam day.'
Full explanation below image
Full Explanation
SSML (Speech Synthesis Markup Language) tags can be embedded in text responses to guide TTS pronunciation; stress; and pacing without altering the visible text content. Disabling TTS removes voice capability. Dictionary entities do not control TTS pronunciation. A pronunciation API via extension adds unnecessary complexity. The correct answer, "Use SSML tags in the response to provide correct pronunciation guidance to the TTS engine", directly satisfies the scenario because it aligns with watsonx Assistant's design principles and the specific capability being tested. The incorrect options ("Disable the text-to-speech engine entirely", "Add the product name as a dictionary entity with phonetic spelling", "Configure a custom extension calling a pronunciation API") may appear relevant but each misses a key requirement or introduces a step that is either unnecessary or belongs to a different workflow. Mastering the distinction between these approaches is essential for effective watsonx Assistant implementations and is a core focus of the Domain 7: Multi-Modal Integration section of the certification exam.