Overview
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.
What you will learn
- 23 written parts, yours for good
- 8h 23m of reading, measured not estimated
- Written for the intermediate level
- Every future revision included
Curriculum
23 sections · 23 parts · 8h 23m37 min free to read · 7h 46m with the project
01Start here1 part · 2 min
- Build an AI Voice Receptionist: the explanationPreview2 min
02Project overview: the Medilane voice receptionist1 part · 12 min
- Project overview: the Medilane voice receptionistPreview12 min
03Module 1: The problem a clinic phone line has1 part · 23 min
- Module 1: The problem a clinic phone line hasPreview23 min
04Module 2: The solution: listen, think, act, speak1 part · 23 min
- Module 2: The solution: listen, think, act, speak23 min
05Module 3: Choosing models and infrastructure1 part · 23 min
- Module 3: Choosing models and infrastructure23 min
06Module 4: High-level design: processes, paths and state1 part · 23 min
- Module 4: High-level design: processes, paths and state23 min
07Module 5: Low-level design: data and protocols1 part · 24 min
- Module 5: Low-level design: data and protocols24 min
08Module 6: Staff sign-in, roles and voice sessions1 part · 24 min
- Module 6: Staff sign-in, roles and voice sessions24 min
09Module 7: Doctors, slots and safe booking1 part · 24 min
- Module 7: Doctors, slots and safe booking24 min
10Module 8: Knowing when the caller has finished1 part · 20 min
- Module 8: Knowing when the caller has finished20 min
11Module 9: Speech to text with Whisper1 part · 20 min
- Module 9: Speech to text with Whisper20 min
12Module 10: English, Hindi and Hinglish1 part · 24 min
- Module 10: English, Hindi and Hinglish24 min
13Module 11: The agent: tools, identity and confirmation1 part · 23 min
- Module 11: The agent: tools, identity and confirmation23 min
14Module 12: Answering from clinic documents1 part · 25 min
- Module 12: Answering from clinic documents25 min
15Module 13: Giving the receptionist a voice1 part · 23 min
- Module 13: Giving the receptionist a voice23 min
16Module 14: The live call: streaming and barge-in1 part · 24 min
- Module 14: The live call: streaming and barge-in24 min
17Module 15: Safety: emergencies, scope and personal data1 part · 24 min
- Module 15: Safety: emergencies, scope and personal data24 min
18Module 16: Models, routing, fallbacks and prompts1 part · 25 min
- Module 16: Models, routing, fallbacks and prompts25 min
19Module 17: Evaluating a voice agent1 part · 24 min
- Module 17: Evaluating a voice agent24 min
20Module 18: Watching calls live1 part · 23 min
- Module 18: Watching calls live23 min
21Module 19: The call page and the staff app1 part · 27 min
- Module 19: The call page and the staff app27 min
22Module 20: Containers and the local stack1 part · 21 min
- Module 20: Containers and the local stack21 min
23Module 21: Deploying to Google Cloud with CI/CD1 part · 22 min
- Module 21: Deploying to Google Cloud with CI/CD22 min
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 |
Source code
The complete, runnable project as one zip: the code the modules explain, with its tests and the files to run and deploy it.
The source code download comes with buying this project.
Submit your build
When the last milestone runs, hand in the repository and three lines about it. That is what the project page will show for you, and what you can send with a job application.
Sign in to submit your build: the repository link and three lines about it.
Reviews
to review this project once you have finished it.