CO/AI Subscribe
Thursday · June 18, 2026 · Issue No. 899
Video

Building voice agents with OpenAI

Watch on YouTube

AI voice agents revolutionize customer service

In a landscape where customer service interactions often feel robotic and frustrating, voice agents powered by cutting-edge AI models are emerging as game-changers for businesses seeking to enhance customer experiences. Dominik Kundel from OpenAI recently demonstrated how the company's Voice Engine and Assistants API can work together to create remarkably natural voice agents that handle complex conversations with nuance and contextual understanding. These tools represent a significant leap forward from the clunky interactive voice response (IVR) systems that have long been the bane of customer service interactions.

Key insights from the presentation:

  • OpenAI's Voice Engine generates remarkably human-like speech that avoids the uncanny valley effect common in traditional text-to-speech systems, enabling more natural customer interactions.

  • The Assistants API provides sophisticated reasoning capabilities and memory retention that allows voice agents to maintain context throughout complex conversations and handle multi-step processes.

  • Creating effective voice agents requires careful design considerations around latency management, error handling, and appropriate voice selection to ensure positive user experiences.

  • The combination of these technologies enables "multimodal" agents that can seamlessly transition between different interaction formats (voice, text, images) depending on context and user needs.

  • OpenAI has implemented strict usage policies and technical safeguards to prevent misuse of voice technology, including voice authentication requirements and prohibitions against impersonation.

The transformative potential of conversational AI

What stands out most from Kundel's presentation is how the integration of advanced voice synthesis with contextual reasoning capabilities fundamentally transforms what's possible in automated customer interactions. Unlike traditional IVR systems that follow rigid decision trees, these new voice agents can maintain context throughout complex, winding conversations, refer back to previously mentioned information, and handle unexpected user inputs with grace.

This matters tremendously for businesses because customer service remains one of the most expensive and challenging operational areas. According to Zendesk's Customer Experience Trends Report, 61% of customers would switch to a competitor after just one bad service experience. The ability to deploy AI voice agents that can handle complex inquiries with human-like understanding could dramatically reduce customer frustration while simultaneously cutting operational costs.

Beyond the basics: Practical applications overlooked

What Kundel's presentation didn't fully explore is how these

Share: X LinkedIn Email
Video Feed

More videos

All videos →
Claude Fable 5: When Capability Meets Economics
Video

Claude Fable 5: When Capability Meets Economics

Anthropic released Cloud Fable 5 with a paradox built in: safeguards sophisticated enough to let a mythosclass model...

Run Agentic AI Entirely on Your Mac—No Cloud, No Latency, No Privacy Tradeoffs
Video

Run Agentic AI Entirely on Your Mac—No Cloud, No Latency, No Privacy Tradeoffs

Apple’s MLX framework is mature enough now that you can run serious agentic AI workflows locally on Silicon...

Hermes Agent Master Class
Video

Hermes Agent Master Class

Welcome to the Hermes Agent Master Class — an 11-episode series taking you from zero to fully leveraging...

CONSULTING

Outsider
Labs.

A management consulting team focused on AI transformations for executives and business owners.

Work with us →