
Product @OpenAI. Founder of Vibely (acquired). Ex-Head of Product.
San Francisco, CA
Joined October 2008
- Tweets210
- Following186
- Followers1.3K
- Likes584
Pinned Tweet
i'll die on this hill-- gpt-live is the most natural voice AI
for max naturalness w prompt-to-voice:
1/ specify accent, timbre, and gender in prompt-to-voice
2/ generate 4+ voices before picking your fav
2/ prompt for lots of backchanneling
4/ leverage custom voices
Teri Yu retweeted
Wild stat. We are now generate more than 4B images per week across ChatGPT and the API, up from the more than 3B per week only 8 weeks ago.
Teri Yu retweeted
Really excited to show off the new playground that @andyisonline and I built for GPT-Live! It’s designed to help build intuition for the model’s bidirectional nature and ability to delegate tasks to other models or agents.
Happy building!
new api voices- let us know what you think! any requests for others?
We've added several new voices for the GPT-Live API - check them out in our new developer playground.
platform.openai.com/audio/li…
Teri Yu retweeted
it’s finally time now to stop chasing streaks in textbook style language apps.
GPT-Live-1 + Praktika avatars now gives you real-time, face-to-face conversation with proactive feedback as you speak.
It feels less like using an app and more like having a tutor in your pocket.
Teri Yu retweeted
You can now talk to a game to generate the world in real time.
I created a playtest using the GPT-Live-1 API that lets you fully change the environment, create new items, weapons, etc.
It's all generated live. This opens up entirely new forms of media 🤯
I built a voice AI agent with GPT-Live-1 on iPhone Duo.
Chat on the left, live map on the right. Ask it to plan a walk around Paris and it updates the route.
Built with Agora Conversational AI and GPT-Live-1. Pretty fun to play with :)
Teri Yu retweeted
GPT-Live-1's voice + a real-time avatar = the language tutor I wish I had.
Full Japanese demo here. French, Korean, Spanish and more in the link below. Pick where you want to travel and start there 👇
Real-time AI experiences are now solved AND open sourced.
We worked closely with @OpenAI to build the best framework for it, combining GPT-Live-1, @TryLiveAvatar, and @HyperFrames_
Check out the demos below and show us what you build with it.
github.com/heygen-com/liveav…
we were legit amazed by GPT-live-1
and when we combined it with @HyperFrames_ and @TryLiveAvatar - and it's magical
here's a demo of a real-time poker coach:
- all cards & ui fully generated on the fly w hyperframes
- GPT-live is the brain and voice
- live avatar makes it all come to life
and we open sourced everything, so anyone can build on top (and yes, the repo is agent-friendly)
new @openai: the world's most natural voice API is out!
gpt-live-1 is full duplex that's
1/ fluid & steerable. leave interruptions & robotic awkwardness behind
2/ expressive & emotion-matching. it's truly hard to distinguish AI
3/ priced for scale. 5c/m + LLM for ambient voice
Teri Yu retweeted
GPT-Image 2.5 is good enough to do stop motion animation now!
ChatGPT Images 2.5—faster, sharper, smarter, with better tools for creating whatever you can dream of.
- Faster image generation to keep your ideas flowing
- Improved fidelity for more natural, recognizable images
- Consistent details across multiple edits
- Comment-based edits to change only what you want


















