Voice Agent

The Voice Agent provides a conversational interface for kiosks, allowing attendees to interact with the system entirely hands-free. This is especially useful for self-service enrollment and accessibility.

1. **Wake and Listen**: The kiosk listens for user speech when activated. Audio is streamed to the transcription service (Speech-to-Text). 2. **Intent Routing**: The transcribed text is sent to an intelligent agent that decides the next action (e.g., answering a question, starting enrollment, or capturing a face). 3. **Voice Response**: The agent formulates a response, which is converted back into natural-sounding speech (Text-to-Speech) and played through the kiosk speakers. 4. **Action Execution**: Simultaneously, the kiosk interface updates to reflect the voice agent's actions, such as navigating to the camera capture screen.

Voice interactions are entirely ephemeral. Audio data is used only for real-time transcription and is not stored or associated with the attendee's permanent record.