18 y/o developer, built a thing which got 15k+ users, contributor @t3dotcodes
Joined January 2026
- Tweets1.3K
- Following146
- Followers167
- Likes3.5K
Pinned Tweet
Local Voice Dictation in now in T3 Code Nightly!
This was a very popular feature request. Thanks to everyone who patiently waited for it.
Had a lot of fun working on this. More amazing features will be coming soon 馃敟
You can now run local transcription models on your @t3dotcodes environments and use it as a dictation hub for any client! Choose among an abundance of models, filter through which best suits your needs, dictionary for words the models don't get right for your voice, and optional customizable post-processing!
Try it out and send feedback!
The first thing I told my dot to do is to call me. It said it could, but it couldn't. @thsottiaux Please allow dots to call us. That would unlock so many things.
Credit to patch-gg.github.io/pixelfx/ for the animation, which I modified with Codex in T3 Code.
Utkarsh retweeted
Thank you @UtkarshUsername for doing the grunt work for this feature!
Did nobody see all the models yet
I put almost the entire T3 Code app inside X. There are so many little things you can do here and they work.
t3code-in-x.pages.dev
I put almost the entire T3 Code app inside X. There are so many little things you can do here and they work.
t3code-in-x.pages.dev
One of the first things I did after getting a dot was tell it to use @pcstyle53's mdfromx.com so that it can read the X posts I send to it. Has been very useful.
Maria's (@maria_rcks) agent just tested my PR and revealed its secret plan. It wants to takeover America and change it to T3 Code Amarica! So is this how T3 Code will earn money?
Utkarsh retweeted
Today we鈥檙e releasing Sarvam Prism, a System One model built on Sarvam 105B for fast, accurate decisions across enterprise workflows.
It scores 71.8 with a median response time of 44 milliseconds, the highest average score among decision models that respond in under 100 milliseconds.
