Track 8: Voice AI Agents, Voice Foundations

Speech-to-Speech Realtime APIs

Build a voice agent on a realtime model.

Status: Coming soon IntermediateVideo lessonAbout 12 min Needs a paid tool
Get notified on YouTube Udemy certificate: coming soon

Course

Production Voice AI Agents

Udemy: coming soon

Tools

Watch first

In this module

  1. How Voice Agents Work: STT, LLM, TTS
  2. Speech-to-Text: Whisper, Deepgram, AssemblyAI
  3. Text-to-Speech for Agents
  4. Latency, Turn-Taking and Interruptions
  5. Speech-to-Speech Realtime APIs
  6. Voice AI for Indian Languages
  7. Voice UX: Prompts, Personas, Fallbacks

The course this lesson belongs to