Build production-grade voice agents, real-time transcription pipelines, and multi-modal AI apps using LiveKit Agents, Whisper, and LLMs
Real-time voice AI is the fastest-growing interface in tech — from customer service bots to AI meeting assistants, voice-first apps are going mainstream. This course teaches you to build production-quality voice AI systems from scratch using LiveKit, the open-source real-time infrastructure platform trusted by thousands of developers.
Backend and full-stack developers comfortable with Python and JavaScript who want to build AI-powered voice, audio, or video products. Prior AI/ML experience is not required but basic familiarity with REST APIs helps.
| Project | Key Technologies |
|---|---|
| Live Transcription App | LiveKit, Whisper, React |
| Voice-Enabled Q&A Bot | LiveKit Agents, GPT-4o, TTS |
| AI Meeting Assistant | LiveKit Cloud, Diarization, Summarization |
| Multi-Language Voice Translator | Whisper, DeepL, LiveKit Egress |
| Voice-Controlled Dashboard | LiveKit, Tool Calling, WebSockets |
| Production Agent Deployment | Docker, LiveKit Cloud, Monitoring |
All times in IST (GMT+5:30)

Deep-Content Learning Series
Celoris deep-content courses are designed for developers who want to go beyond surface-level tutorials and truly understand how things work.