Olivia
Online
Vignesh Angurajan
@VigneshAnguraj
Founder, Timegravity Labs. Independent AI researcher. Small models from scratch, efficient training, open recipes. Building in the open from Coimbatore.
Coimbatore, Tamilnadu, India
Joined June 2026
81 Following
25 Followers
88 Posts
Β Pinned Tweet
I built a tool that draws what I say, while I say it.
Everything in this video is generated LIVE. Nothing pre-made, nothing edited in. I speak, it draws. Spoken numbers become real charts. Processes become diagrams. Stories become scenes. It cannot hallucinate a number. if I don't say it, it doesn't draw it.
It runs entirely on one PC on my desk. No cloud. No internet. One GPU.
This is what genuinely excites me: we keep talking about AI's potential, but so much of it is still untapped. This is one small piece of it. Imagine classrooms where the board illustrates the teacher's words as she speaks. Online tuition where every concept turns visual instantly. Speech made visible in real time for deaf and hard-of-hearing students. Storytellers narrating worlds into existence.
To be clear: everything in the video, the product intro, the revenue numbers, are imaginary, just scenarios I invented to show what it can do.
It is not polished. It mishears words sometimes, characters change faces between scenes. That is exactly why I am open sourcing it, so we can improve it together.
I searched for another tool that does this, live and locally. Couldn't find one.
Repo coming soon.
@CuriosityonX Any gravity or time related issues? [email protected] π
@denk_tweets Are you talking about me? π 10 years building AI systems quietly. Then quit my job to pursue my startup dream and last month I started sharing my work publicly
I built a tool that draws what I say, while I say it.
Everything in this video is generated LIVE. Nothing pre-made, nothing edited in. I speak, it draws. Spoken numbers become real charts. Processes become diagrams. Stories become scenes. It cannot hallucinate a number. if I don't say it, it doesn't draw it.
It runs entirely on one PC on my desk. No cloud. No internet. One GPU.
This is what genuinely excites me: we keep talking about AI's potential, but so much of it is still untapped. This is one small piece of it. Imagine classrooms where the board illustrates the teacher's words as she speaks. Online tuition where every concept turns visual instantly. Speech made visible in real time for deaf and hard-of-hearing students. Storytellers narrating worlds into existence.
To be clear: everything in the video, the product intro, the revenue numbers, are imaginary, just scenarios I invented to show what it can do.
It is not polished. It mishears words sometimes, characters change faces between scenes. That is exactly why I am open sourcing it, so we can improve it together.
I searched for another tool that does this, live and locally. Couldn't find one.
Repo coming soon.
@yowtfahhh India with zero budget
I built a tool that draws what I say, while I say it.
Everything in this video is generated LIVE. Nothing pre-made, nothing edited in. I speak, it draws. Spoken numbers become real charts. Processes become diagrams. Stories become scenes. It cannot hallucinate a number. if I don't say it, it doesn't draw it.
It runs entirely on one PC on my desk. No cloud. No internet. One GPU.
This is what genuinely excites me: we keep talking about AI's potential, but so much of it is still untapped. This is one small piece of it. Imagine classrooms where the board illustrates the teacher's words as she speaks. Online tuition where every concept turns visual instantly. Speech made visible in real time for deaf and hard-of-hearing students. Storytellers narrating worlds into existence.
To be clear: everything in the video, the product intro, the revenue numbers, are imaginary, just scenarios I invented to show what it can do.
It is not polished. It mishears words sometimes, characters change faces between scenes. That is exactly why I am open sourcing it, so we can improve it together.
I searched for another tool that does this, live and locally. Couldn't find one.
Repo coming soon.
I built a tool that draws what I say, while I say it.
Everything in this video is generated LIVE. Nothing pre-made, nothing edited in. I speak, it draws. Spoken numbers become real charts. Processes become diagrams. Stories become scenes. It cannot hallucinate a number. if I don't say it, it doesn't draw it.
It runs entirely on one PC on my desk. No cloud. No internet. One GPU.
This is what genuinely excites me: we keep talking about AI's potential, but so much of it is still untapped. This is one small piece of it. Imagine classrooms where the board illustrates the teacher's words as she speaks. Online tuition where every concept turns visual instantly. Speech made visible in real time for deaf and hard-of-hearing students. Storytellers narrating worlds into existence.
To be clear: everything in the video, the product intro, the revenue numbers, are imaginary, just scenarios I invented to show what it can do.
It is not polished. It mishears words sometimes, characters change faces between scenes. That is exactly why I am open sourcing it, so we can improve it together.
I searched for another tool that does this, live and locally. Couldn't find one.
Repo coming soon.
@RaminNasibov What about this one
I built a tool that draws what I say, while I say it.
Everything in this video is generated LIVE. Nothing pre-made, nothing edited in. I speak, it draws. Spoken numbers become real charts. Processes become diagrams. Stories become scenes. It cannot hallucinate a number. if I don't say it, it doesn't draw it.
It runs entirely on one PC on my desk. No cloud. No internet. One GPU.
This is what genuinely excites me: we keep talking about AI's potential, but so much of it is still untapped. This is one small piece of it. Imagine classrooms where the board illustrates the teacher's words as she speaks. Online tuition where every concept turns visual instantly. Speech made visible in real time for deaf and hard-of-hearing students. Storytellers narrating worlds into existence.
To be clear: everything in the video, the product intro, the revenue numbers, are imaginary, just scenarios I invented to show what it can do.
It is not polished. It mishears words sometimes, characters change faces between scenes. That is exactly why I am open sourcing it, so we can improve it together.
I searched for another tool that does this, live and locally. Couldn't find one.
Repo coming soon.
Waiting eagerly. I need to mention that my application uses Qwen3.5 9B model. Demo link: https://t.co/ILqoGpVK8k
Got you covered bro, 27B is landing this week
@NikhilLamba6 Image (scene stills): Tongyi-MAI/Z-Image-Turbo
Video (animation): Lightricks/LTX-Video
I built a tool that draws what I say, while I say it.
Everything in this video is generated LIVE. Nothing pre-made, nothing edited in. I speak, it draws. Spoken numbers become real charts. Processes become diagrams. Stories become scenes. It cannot hallucinate a number. if I don't say it, it doesn't draw it.
It runs entirely on one PC on my desk. No cloud. No internet. One GPU.
This is what genuinely excites me: we keep talking about AI's potential, but so much of it is still untapped. This is one small piece of it. Imagine classrooms where the board illustrates the teacher's words as she speaks. Online tuition where every concept turns visual instantly. Speech made visible in real time for deaf and hard-of-hearing students. Storytellers narrating worlds into existence.
To be clear: everything in the video, the product intro, the revenue numbers, are imaginary, just scenarios I invented to show what it can do.
It is not polished. It mishears words sometimes, characters change faces between scenes. That is exactly why I am open sourcing it, so we can improve it together.
I searched for another tool that does this, live and locally. Couldn't find one.
Repo coming soon.
Introducing a revolutionary AI product with a new application of AI. one that looks beyond where language models are typically used today. Open sourcing the entire application in a week.
Educators and explainers just got superpowered.
No more losing a day preparing presentations. You speak, and your words become images, charts, diagrams, and video, LIVE , as you talk. Humans have always had one way to explain: describe it. Now there are two. Show what you speak.
The magical mirror from the comics, became real, with the help of tech. AI's potential is still underutilised.
I built a tool that draws what I say, while I say it.
Everything in this video is generated LIVE. Nothing pre-made, nothing edited in. I speak, it draws. Spoken numbers become real charts. Processes become diagrams. Stories become scenes. It cannot hallucinate a number. if I don't say it, it doesn't draw it.
It runs entirely on one PC on my desk. No cloud. No internet. One GPU.
This is what genuinely excites me: we keep talking about AI's potential, but so much of it is still untapped. This is one small piece of it. Imagine classrooms where the board illustrates the teacher's words as she speaks. Online tuition where every concept turns visual instantly. Speech made visible in real time for deaf and hard-of-hearing students. Storytellers narrating worlds into existence.
To be clear: everything in the video, the product intro, the revenue numbers, are imaginary, just scenarios I invented to show what it can do.
It is not polished. It mishears words sometimes, characters change faces between scenes. That is exactly why I am open sourcing it, so we can improve it together.
I searched for another tool that does this, live and locally. Couldn't find one.
Repo coming soon.
@naval True https://t.co/AVIkCGJfhN
https://t.co/9DDcF24Nnt
I built a tool that draws what I say, while I say it.
Everything in this video is generated LIVE. Nothing pre-made, nothing edited in. I speak, it draws. Spoken numbers become real charts. Processes become diagrams. Stories become scenes. It cannot hallucinate a number. if I don't say it, it doesn't draw it.
It runs entirely on one PC on my desk. No cloud. No internet. One GPU.
This is what genuinely excites me: we keep talking about AI's potential, but so much of it is still untapped. This is one small piece of it. Imagine classrooms where the board illustrates the teacher's words as she speaks. Online tuition where every concept turns visual instantly. Speech made visible in real time for deaf and hard-of-hearing students. Storytellers narrating worlds into existence.
To be clear: everything in the video, the product intro, the revenue numbers, are imaginary, just scenarios I invented to show what it can do.
It is not polished. It mishears words sometimes, characters change faces between scenes. That is exactly why I am open sourcing it, so we can improve it together.
I searched for another tool that does this, live and locally. Couldn't find one.
Repo coming soon.
@MichaelDell Yes
I built a tool that draws what I say, while I say it.
Everything in this video is generated LIVE. Nothing pre-made, nothing edited in. I speak, it draws. Spoken numbers become real charts. Processes become diagrams. Stories become scenes. It cannot hallucinate a number. if I don't say it, it doesn't draw it.
It runs entirely on one PC on my desk. No cloud. No internet. One GPU.
This is what genuinely excites me: we keep talking about AI's potential, but so much of it is still untapped. This is one small piece of it. Imagine classrooms where the board illustrates the teacher's words as she speaks. Online tuition where every concept turns visual instantly. Speech made visible in real time for deaf and hard-of-hearing students. Storytellers narrating worlds into existence.
To be clear: everything in the video, the product intro, the revenue numbers, are imaginary, just scenarios I invented to show what it can do.
It is not polished. It mishears words sometimes, characters change faces between scenes. That is exactly why I am open sourcing it, so we can improve it together.
I searched for another tool that does this, live and locally. Couldn't find one.
Repo coming soon.
I built a tool that draws what I say, while I say it.
Everything in this video is generated LIVE. Nothing pre-made, nothing edited in. I speak, it draws. Spoken numbers become real charts. Processes become diagrams. Stories become scenes. It cannot hallucinate a number. if I don't say it, it doesn't draw it.
It runs entirely on one PC on my desk. No cloud. No internet. One GPU.
This is what genuinely excites me: we keep talking about AI's potential, but so much of it is still untapped. This is one small piece of it. Imagine classrooms where the board illustrates the teacher's words as she speaks. Online tuition where every concept turns visual instantly. Speech made visible in real time for deaf and hard-of-hearing students. Storytellers narrating worlds into existence.
To be clear: everything in the video, the product intro, the revenue numbers, are imaginary, just scenarios I invented to show what it can do.
It is not polished. It mishears words sometimes, characters change faces between scenes. That is exactly why I am open sourcing it, so we can improve it together.
I searched for another tool that does this, live and locally. Couldn't find one.
Repo coming soon.
@TheAhmadOsman This is what possible with local ai https://t.co/yd0XWTatUW
I built a tool that draws what I say, while I say it.
Everything in this video is generated LIVE. Nothing pre-made, nothing edited in. I speak, it draws. Spoken numbers become real charts. Processes become diagrams. Stories become scenes. It cannot hallucinate a number. if I don't say it, it doesn't draw it.
It runs entirely on one PC on my desk. No cloud. No internet. One GPU.
This is what genuinely excites me: we keep talking about AI's potential, but so much of it is still untapped. This is one small piece of it. Imagine classrooms where the board illustrates the teacher's words as she speaks. Online tuition where every concept turns visual instantly. Speech made visible in real time for deaf and hard-of-hearing students. Storytellers narrating worlds into existence.
To be clear: everything in the video, the product intro, the revenue numbers, are imaginary, just scenarios I invented to show what it can do.
It is not polished. It mishears words sometimes, characters change faces between scenes. That is exactly why I am open sourcing it, so we can improve it together.
I searched for another tool that does this, live and locally. Couldn't find one.
Repo coming soon.
Mars landing audio from 'Perseverance Rover's Descent and Touchdown on Mars (Official NASA Video)', public domain.
Last Seen Users on Sotwe
pace kontol
Seen from Singapore
pecinta ibu kandung
Seen from Indonesia
ΩΩΨ§Ψ―Ψ§Ψ±
Seen from Pakistan
yasak aΕk β‘
Seen from Turkey
Meme hastasi
Seen from Turkey
Babacann
Seen from Turkey
Xoxo
Seen from India
Afra
Seen from Turkey
NaypyiTaw Kaung Lay
Seen from Singapore
olgun ve ΕiΕman sikicisi
Seen from Turkey
Most Popular Users
Elon Musk
@elonmusk
241.3M followers
Barack Obama
@barackobama
119.1M followers
Cristiano Ronaldo
@cristiano
113M followers
Donald J. Trump
@realdonaldtrump
111.8M followers
Narendra Modi
@narendramodi
107.1M followers
Rihanna
@rihanna
98.3M followers
NASA
@nasa
92.3M followers
Justin Bieber
@justinbieber
91.5M followers
KATY PERRY
@katyperry
89.1M followers
Taylor Swift
@taylorswift13
83M followers
Lady Gaga
@ladygaga
74.5M followers
Virat Kohli
@imvkohli
72.1M followers
Kim Kardashian
@kimkardashian
70.5M followers
YouTube
@youtube
68.8M followers
Neymar Jr
@neymarjr
65M followers
Bill Gates
@billgates
64.7M followers
The Ellen Show
@theellenshow
62.4M followers
Selena Gomez
@selenagomez
62.2M followers
CNN
@cnn
61.8M followers
X
@x
60.8M followers