Dense Slides: Building voice agents with OpenAI — Dominik Kundel, OpenAI

Source Video

Building voice agents with OpenAI — Dominik Kundel, OpenAI

Method

This deck is slide-only. The existing captured video frame set supplies candidate frames, then local OpenCV rejects sponsor/title/speaker-only frames, crops visible slide surfaces, deduplicates, and saves the cropped slide images.

Cropped Visible Slides

Recreated text/layout view: open HTML recreation
AI slide classifier: content_slide confidence 0.99
Text source: agent_vision.

Slide text:

#workshop-openai-voice-agents

Starter repository

https://github.com/dkundel-openai/aie-voice-agents-workshop

Documentation

https://openai.github.io/openai-agents-js/

Recreated text/layout view: open HTML recreation
AI slide classifier: content_slide confidence 0.99
Text source: agent_vision.

Slide text:

Voice agents provide a wide range of benefits

• More flexible than traditional IVRs (no need to outline complex phone trees, multilingual). Let human agents focus on complex cases

• Makes your AI more accessible to broader parts of the population

• More information dense and personalized than just text by introducing emotions

• Can act as an API to the real-world by leading conversations with other businesses

Recreated text/layout view: open HTML recreation
AI slide classifier: content_slide confidence 0.98
Text source: agent_vision.

Slide text:

building voice agents

Start small with a clear goal

Build evals and guardrails early. Collect feedback

Customize and create a personalized brand

Recreated text/layout view: open HTML recreation
AI slide classifier: content_slide confidence 0.98
Text source: agent_vision.

Slide text:

Agents SDK automatically sends traces to the Traces dashboard in your OpenAI account

Review conversations

Replay audio

Inspect tool calls

Classification audit: raw/sources/slide-ai-classification/dense/iXhba366fQc/audit.json