OpenAI #GPT4o #Audio Extremely excited to share the results of what I've been working on for 2 years GPT models now natively understand audio: you can talk to the Transformer itself! The feeling is hard to describe so I can't wait for people to speak to it #HearTheAGI 🧵1/N

here is o1, a series of our most capable and aligned models yet: openai.com/index/learning… o1 is still flawed, still limited, and it still seems more impressive on first use than it does after you spend more time with it.

Excited to share the results of a long running research program aimed at getting models to go beyond imitation learning and to think for themselves! It's been an absolute joy working closely with Jerry Tworek Jakub Pachocki Szymon Sidor Lukasz Kaiser Ilya Sutskever William Fedus Wojciech Zaremba

Today's the day! sora.com Included with ChatGPT Plus/Pro!

sora is launching today to all chatgpt pro and plus users! it's been a big effort to make this possible + i think the product is really fun & intuitive. my fav thing to do is generate fake historical found footage. video inpainting is also really strong. have fun!

Sora @ sora.com Available today. Included with your ChatGPT Plus and Pro accounts. It's been an incredible experience building this with Bill Peebles Aditya Ramesh Rohan Sahai and the whole team.

Today’s deployment is only possible with our new model, Sora Turbo. Huge shoutout to Bram Wallace and Jure Zbontar who spearheaded Sora model acceleration research!

Stoked to finally be able to say what I've been working on this year! There's so much exciting post-training research ahead of us, we're just getting started over here

It's rare for someone to be both a world-class researcher and such an amazing leader for the research team. Bill Peebles is one the most talented people I've ever worked with!

Working on Sora with such an incredible and talented team is truly the experience of a lifetime. I hope you love Sora as much as we loved creating it!

catching my breath from yesterday’s excitement. it’s been awesome to see all the love for the Sora UI it’s been such a blast dreaming up new was to interact with this bleeding edge technology with Joey Flynn he is such a legend no plans on stopping anytime soon

Still buzzing from having the opportunity to be a part of the Sora release yesterday. It’s rare to be able to work on the technology that excites you the most alongside a small team of people you admire the most — Rohan Sahai 💀 Joe Taylor 💀 David Schnurr Wesam 🇵🇸 Boyang Niu starr jeev

Excited to open the floodgates! It's been very inspiring to see Rohan Sahai lead the product team and bring a new product surface from 0-1.

Proud to finally see an American video model on top! Sora was developed and trained in the United States. 🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸

Shipmas Day 13 Sora Bonus?? 🎉✨ We’ve also rolled out Sora access to all Teams users, upgraded our blend feature, and enabled shared links so you can share Sora creations with friends—even if they don’t have an account.

Thrilled to see this launch -- and inspiring to see Gabriel Goh continuously making the system better and better over the course of the project!

4o image generation is finally out! Gabriel Goh, A Jabri, Lu Liu, Kenji Hata, Jianfeng Wang, dmed M have really made something magical, go try it out!!

The 4o image gen demand has been absolutely incredible. Been super fun to watch the Sora feed fill up with great content . Our GPUs are also melting in Sora land unfortunately so you may see longer wait times / capacity issues over coming days. We’ll be working hard to get back

“Thinking with Images” has been one of our core bets in Perception since the earliest o-series launch. We quietly shipped o1 vision as a glimpse—and now o3 and o4-mini bring it to life with real polish. Huge shoutout to our amazing team members, especially: - Brandon McKinzie, for