Voice systems
Adaptive Voice Interview.
Participants answer by voice or text. A finite-state machine tracks the interview, uses the answer to choose a branch, and asks the next question. Each turn also yields structured fields.
Architecture
5 servicesSelected service
Interview client
The Next.js client collects answers and displays the next question.
Connections
- To Send interview answers over a WebSocket
- To Request dictation and read-aloud
View all connections
- Interview client → FastAPI interview APISend interview answers over a WebSocket
- Interview client → Azure AI SpeechRequest dictation and read-aloud
- FastAPI interview API → Interview state machineProcess the current interview turn
- Interview state machine → Azure OpenAIExtract fields and evaluate the next question
Technology stack
Next.js
FastAPI
Azure AI Speech
Azure OpenAI
Azure Container Apps
Azure Container Registry
Azure Blob Storage
Next projectVoice Agent Practice Rooms