Podcast Episode Details
Back to Podcast Episodes
Agents at Work 15: The Voice of AI Agents w/ Tom Shapland (LiveKit)
Season 1 Episode 15
In this episode of Agents at Work, Jordi Montes sits down with Tom Shapland , product manager at LiveKit, the open-source platform powering real-time audio/video. They power the voice agents behind ChatGPT’s audio interface.
They dive into:
How a LiveKit side project became the voice pipeline for ChatGPT
The rise of cascaded pipelines vs. audio-to-audio agents
What makes voice turn-taking so tricky (and how to fix it)
The role of tone, latency, and emotion in building natural-sounding AI
Why voice agents are more than just a feature—they’re the future interface
Tom shares his journey from building agtech startups to surfing the wave of voice AI infrastructure. He unpacks what it really means to bring machines closer to humans, and why we’re entering a golden age of ambient, always-on, emotionally aware assistants.
Whether you’re an engineer, product manager, or just someone dreaming of yelling at your printer and getting a helpful response this episode is a must-listen.
Try it at https://livekit.io
Published on 2 months, 2 weeks ago