Exam AI-102 topic 3 question 35 discussion

1. Speech-to-text 2. Text-to-speech and Translator https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/speech-to-text With real-time speech to text, the audio is transcribed as speech is recognized from a microphone or file. https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/text-to-speech ext to speech enables your applications, tools, or devices to convert text into humanlike synthesized speech. The text to speech capability is also known as speech synthesis. Use humanlike prebuilt neural voices out of the box, or create a custom neural voice that's unique to your product or brand.

Speech-to-text is CORRECT because it is the service designed to convert spoken language into written text. This is exactly what is needed to capture inbound voice messages as text from French-speaking and German-speaking callers. Text-to-speech and Translator is CORRECT because the Translator service can be used to translate the captured text from French or German to English, and the Text-to-speech service can then convert the translated text into spoken English to replay the messages.

1. Speech-to-text 2. Text-to-speech and Translator

1. Speech-to-text 2. Text-to-speech and Translator

Speech-to-text Text-to-speech and Translator

A modified version of this was in the exam today.

answer is correct