Head of Realtime AI @OpenAI. Created WebRTC. Past: CTO @ultravox_dot_ai, Distinguished Engineer @google (Stadia, Meet/Duo), AIM. Amateur mathematician/musician.
Joined February 2007
- Tweets 5,440
- Following 121
- Followers 14,235
- Likes 6,235
450 Photos and videos
Pinned Tweet
May 6
New post on the OpenAI eng blog from two engineers on our Realtime AI team here in Seattle, outlining how we designed our v2 realtime infra and how we've optimized it for easy scalability and low latency. Check it out!
openai.com/index/delivering-…
2
3
35
4,132
Justin Uberti retweeted
May 30
Watch me control my computer with just my voice. This is the future of operating systems.
No hands.
GPT-Realtime 2.0 is very, very underrated.
Demo:
931
839
14,123
3,708,884
May 22
If you’re using gpt-realtime-whisper as the ASR model in a cascade pipeline, you can try this as an end-of-utterance signal.
May 20
there's nothing exactly like that right now, although punctuation timeout on deltas would probably work quite well
3
17
4,246
Justin Uberti retweeted
May 18
The bitter lesson in 26 words:
Don’t be distracted by human knowledge, as AI has been historically.
Instead focus on methods for creating knowledge that scale with computation, like search and learning.
136
973
7,416
575,075
Justin Uberti retweeted
May 8
.@sama posted this week that he's "pretty excited for voice models to get great."
But when will that happen?
What @OpenAI's @juberti told @jameswilsterman at Cerebral Valley Voice:
1
3
1,201
May 8
cool realtime UX demo
May 7
Using @OpenAI gpt-realtime-2 to get a glimpse of future voice-first experiences.
A market dashboard you don’t click through.
You direct it.
Say, “Focus on Apple,” and the whole interface changes.
Ask, “How did it do over the last 30 days?” and the chart updates.
Say, “Go back,” and the market view returns.
No menus.
No filters.
No hunting around.
Just intent.
What makes this model especially interesting is the interaction loop: you can interrupt it, add more context, change direction, and it keeps reasoning in real time while updating the experience around you.
The interface doesn’t ask you to navigate.
It just takes you there.
12
2,390
Justin Uberti retweeted
Apr 9
We're looking for a creative iOS engineer to join our realtime AI team here at OpenAI Seattle to help build the future of human-AI interaction. If you know WebRTC, AVFoundation, and/or Core Audio and like open-ended challenges, apply at openai.com/careers/ios-softw… or just DM!
8
23
274
42,046
May 8
Incredible. No notes.
May 8
The Sam Altman and @miramurati texts from the day he got fired from @OpenAI in 2023 just became evidence in the @elonmusk v. @sama trial.
It felt like a meaningful moment in AI history, so I turned it into a musical.
The lyrics are the texts.
1
3
1,636
Justin Uberti retweeted
May 7
Congrats to @OpenAI for taking the top spot on our Audio MultiChallenge S2S leaderboard with the release of GPT‑Realtime‑2 🥇
GPT-Realtime-2 more than doubles GPT-Realtime-1.5 on instruction retention, rising from 36.7% to 70.8% APR, and also stands out on voice editing, especially when users repair or revise what they are saying in real time – crucial for voice agent use cases.
Excited to see the pace of progress as voice AI accelerates.
27
57
614
74,335
May 7
gpt-realtime-2 shows a 15pp improvement (vs 1.5) on Big Bench Audio, and is now close to saturation.
Voice agents are so back!!
Today we’re launching 3 new realtime audio models in the API:
🎙️ GPT-Realtime-2
GPT-5-class reasoning for voice agents that can use tools, recover from interruptions, and carry longer conversations with 128K context
🌍 GPT-Realtime-Translate
Live speech translation from 70 input languages into 13 output languages
📝 GPT-Realtime-Whisper
Streaming transcription as people speak
This is the next step for voice apps:
listen → reason → translate → transcribe → act
Available today in the Realtime API! Enjoy!
5
30
5,044
May 7
Just added a delay selector to allow control of the latency/accuracy tradeoff. realtyper.val.run?delay=mini…
2
1
18
3,049
May 7
Guess who's back, back again. Whisper, but now with realtime streaming. Check out the new gpt-realtime-whisper transcription model in my realtyper.val.run demo.
6
7
43
4,661
May 7
Updated my hello-realtime demo to use the new gpt-realtime-2 model (now with reasoning). Check it out at hello-realtime.val.run, or call 425-800-0042!
2
3
21
1,790
May 7
Big Realtime API drop!
- gpt-realtime-2, our first realtime model with reasoning
- gpt-realtime-translate for voice-to-voice translation
- gpt-realtime-whisper for streaming transcription
Docs: developers.openai.com/api/do…
May 7
Voice agents are getting more capable.
Here’s what’s new:
• GPT-Realtime-2 for voice agents that reason and take action
• GPT-Realtime-Translate enabling translation from 70 input languages into 13 output languages
• GPT-Realtime-Whisper, making transcription even faster
7
5
56
4,388
May 6
The ICE protocol (RFC 5245) was designed for peer to peer flows, but it’s turned out to be remarkably versatile even in client-server scenarios, allowing for easy authentication, stateless routing, and realtime path selection. Details in our post below: openai.com/index/delivering-…
3
25
2,156
May 6
the UX of the agentic future
May 5
pretty excited for voice models to get great
its interesting to watch how people are already starting to change the way they interface with AI
2
2
59
12,579
May 6
Tomorrow!
Apr 7
Will be speaking at the Cerebral Valley Voice Summit on May 6 in SF, along with some other great folks in this space! cerebralvalleyvoice.com
4
1,218