A kiosk must hear a question and reply aloud. Which service provides the voice parts?
Why A is the answer
Azure Speech in Foundry Tools
Azure Speech provides speech to text and text to speech.
In detail
- Azure Speech provides both the listening and the speaking.
- A language model can write the reply in between.
Use case
An illustrative scenario, not a real incident.
A museum kiosk hears a visitor and replies aloud. Azure Speech in Foundry Tools provides both voice parts.
See it in different ways
flowchart LR A["Spoken question"] --> B["Speech to text"] B --> C["Model answers"] C --> D["Text to speech"] D --> E["Spoken answer"]
sequenceDiagram participant U as User participant S as Azure Speech participant M as Model U->>S: Spoken question S->>M: Text M-->>S: Text reply S-->>U: Spoken reply
flowchart TD
Q{"What does the kiosk need?"}
Q -->|"Voice in and out"| A0["Azure Speech"]
Q -->|"Written answers"| A1["A language model"]Key point: Azure Speech handles hearing and speaking.
Why the other options are wrong
- B. A vector index
- A vector index searches content.
- C. A content filter
- A content filter checks text.
- D. An image generation model
- An image model creates images.