OpenAI GPT-4o Speech Models in 6 Minutes
OpenAI Enhances Speech Models: New Text-to-Speech & Speech-to-Text Innovations In today’s video, we delve into OpenAI’s latest release of three new audio models. Discover the enhanced speech-to-text models superior to Whisper, and a groundbreaking text-to-speech model allowing precise control over timing and emotion. Learn how to try these models for free on OpenAI’s interface, designed with a distinctive, practical look by Teenage Engineering. Explore various voice types, personality settings, and pronunciation controls. We also compare new models, GPT-4 Transcribe and GPT-4 Mini Transcribe, against other state-of-the-art models. The video provides cost details and a simple guide to getting started with these models using Python, JavaScript, or cURL scripts in the OpenAI API. Additionally, insights into logging, tracing, and example setups in OpenAI Agents SDK are shared. Don’t miss out on the future of AI voice applications! Links: https://www.openai.fm/ https://www.youtube.com/watch?v=lXb0L16ISAc https://platform.openai.com/playground/tts https://platform.openai.com/docs/guides/audio https://platform.openai.com/docs/guides/speech-to-text https://platform.openai.com/docs/guides/text-to-speech https://platform.openai.com/docs/api-reference/introduction https://github.com/openai/openai-agents-python/tree/main/examples 00:00 Introduction to OpenAI’s New Audio Models 00:16 Exploring the Interface and Features 01:01 Demonstration of Text-to-Speech Capabilities 02:21 New Speech-to-Text Models and Their Performance 03:18 Getting Started with OpenAI’s API 04:21 Using OpenAI Agents SDK 05:15 Conclusion and Final Thoughts
Recent Videos
Hermes Agent Master Class
https://www.youtube.com/watch?v=R3YOGfTBcQg Welcome to the Hermes Agent Master Class — an 11-episode series taking you from zero to fully leveraging every feature of Nous Research's open-source agent. In this first episode, we install Hermes from scratch on a brand new machine with no prior skills or memory, walk through full configuration with OpenRouter, tour the most important CLI and slash commands, and run our first real task: a competitor research report on a custom children's book AI business idea. Every future episode will build on this fresh install so you can see the compounding value of the agent in real time....
Apr 29, 2026Andrej Karpathy – Outsource your thinking, but you can’t outsource your understanding
https://www.youtube.com/watch?v=96jN2OCOfLs Here's what Andrej Karpathy just figured out that everyone else is still dancing around: we're not in an era of "better models." We're in a different era of computing altogether. And the difference between understanding that and not understanding it is the difference between being a vibe coder and being an agentic engineer. Last October, Karpathy had a realization. AI didn't stop being ChatGPT-adjacent. It fundamentally shifted. Agentic coherent workflows started to actually work. And he's spent the last three months living in side projects, VB coding, exploring what's actually possible. What he found is a framework that explains...
Mar 30, 2026Andrej Karpathy on the Decade of Agents, the Limits of RL, and Why Education Is His Next Mission
A summary of key takeaways from Andrej Karpathy's conversation with Dwarkesh Patel In a wide-ranging conversation with Dwarkesh Patel, Andrej Karpathy — former head of AI at Tesla, founding member of OpenAI, and creator of some of the most popular AI educational content on the internet — shared his views on where AI is headed, what's still broken, and why he's now pouring his energy into education. Here are the key takeaways. "It's the Decade of Agents, Not the Year of Agents" Karpathy's now-famous quote is a direct pushback on industry hype. Early agents like Claude Code and Codex are...