Build an AI Voice Receptionist: the explanation
A working voice receptionist for a fictional clinic in Pune, taken apart in illustrated modules. Callers talk in the browser in English, Hindi or Hinglish; the receptionist answers from the clinic's own documents, books, moves and cancels appointments after checking who is calling, stops talking the moment the caller interrupts, and sends every emergency straight to 112 and the front desk. Everything runs on open models: Whisper for listening, open-weight language models on Groq for thinking, and Kokoro for speaking on an ordinary CPU.
Who it is for: anyone who knows a little Python and wants to understand, rebuild or extend a real-time voice AI application, from beginners to working engineers. Each module says what to read first.
How each module is laid out
| Section | Answers |
|---|---|
| Where this fits | the same system map in every module, with this module's parts highlighted |
| What it does | the idea in one picture, then each production practice at a glance: what, why, how, when, where |
| Use cases and examples | the same practice in this clinic and in other industries |
| How it works | the mechanism step by step, one figure per step, with real values |
| Code tour | the real files, short excerpts, every line explained, concept boxes for new ideas, and a "what happens when" trace |
| Design decisions | what was chosen, the alternatives and why, with measured numbers, and when to choose differently |
| What can go wrong | failures and attacks, how the code handles each, and the test that proves it |
| Try it yourself | exact commands and what you should see |
| Check yourself, Key terms | a short quiz and a glossary |
Figures use one colour language: blue is our system, amber is a model or anything uncertain, green is correct or safe, red is failure or attack, grey is background.