Video course · 8 chapters · 21 min · certificate
Voice AI Essentials: Building Real-Time, Multi-Turn, and Multimodal Agents
Voice AI essentials from practitioners: a voice AI course collaboration, the key components of voice agents, future voice and video trends, business and consumer adoption, open models, integration challenges with LLMs, telephony innovations and voice at home.
What you'll learn
- Name the key components of a voice agent
- Explain where voice AI is monetising
- Assess open models for voice
- Identify hard problems like latency and turn-taking
- Understand telephony integration
- Anticipate voice and video agent trends
Chapters
8 chapters · 20:50-
2:06
01Intro Members
Course collaboration
A lightning pod.
-
2:20
02Architecture Members
Key components
What makes voice different.
-
1:26
03Trends Members
Future voice and video trends
Real-time video agents.
-
2:55
04Market Members
Business and consumer adoption
Monetisable use cases.
-
2:59
05Open models Members
Open models and trends
Frameworks and models.
-
2:52
06Challenges Members
Integration challenges
The hard problems.
-
3:11
07Telephony Members
Telephony and voice access
Phones and parallel tasks.
-
3:01
08Future Members
Voice at home and community
Robots and home automation.