AI Series Course

AI Voice Assistant Robot Course

Download Course Materials

Course Code: TC-AIVAR-C-06

Audience

Grades P4 to S3

Class Size

20–40 students

Time

Total duration: 6 hours

Each session: 1.5 hours (4 sessions)

Location

On-campus classroom (Wi-Fi and computers required)

Before Class

Install the following software on classroom computers before the course starts.

Expected Learning Outcomes

  1. Understand the roles and applications of AI agents and voice robots in modern industries
  2. Design expressive robot-eye interfaces and build basic interactive UIs with HTML, CSS, and Python
  3. Use JavaScript recording, Python API calls, and voice technologies (STT/TTS)
  4. Understand API workflow principles and communication protocols, and manage API keys correctly
  5. Design and refine AI prompts to create a custom intelligent voice assistant

Assessment Policy

  • •Class participation and learning attitude: 20%
  • •Programming implementation and functional completeness: 30%
  • •Creativity and final presentation: 50%

Tools & Resources

  • •$660 Mastercard gift card (Augment, Poe.com, Cantonese.ai subscriptions, 1 card per student)
  • •Laptop
  • •Internet access

Teaching Plan

SessionTopicExpected Learning OutcomesDuration
1Introduction to AI robots and voice agents
  • •Explain basic concepts of robots, artificial intelligence, and AI agents
  • •Give real-world examples of AI in current and future robotic applications
  • •Understand functions of voice agents in smart assistants and service robots
  • •Propose a concept for a personalized AI voice agent
1.5 hours
2Robot interface design and Python basics
  • •Explain the importance of expression interfaces in human-robot interaction
  • •Design an eye interface with HTML and CSS
  • •Learn basic Python syntax
  • •Understand how front-end and back-end logic connect
  • •Use Python to control interface behavior or dynamic effects
1.5 hours
3AI-assisted coding and prompt engineering
  • •Explain fundamentals and use cases of speech-to-text (STT) and text-to-speech (TTS)
  • •Understand API fundamentals and communication protocols
  • •Learn to obtain and use API keys for AI tools and manage access securely
  • •Record voice with JavaScript and convert it into API-ready formats
  • •Call STT/TTS APIs with Python to convert between text and speech
  • •Observe limitations and errors in speech recognition and suggest improvements
1.5 hours
4Final showcase and AI ethics
  • •Use Python to call LLM APIs and work with different LLM models
  • •Modify LLM system prompts to create a voice assistant with personal style
  • •Integrate front-end interface, STT, LLM, and TTS modules into a complete voice-interaction workflow
  • •Demonstrate the completed voice-agent project
  • •Explain system design logic and the impact of AI on society and creative work
1.5 hours