@huwprosser: yes actually…. #jarvis #ironman #vr #programming

mikolaj_oczki :

bro i love your videos and i have few questions 1:is your jarvis on computer system or some app 2:is that windows or linux or something i dont know 3:where you using python 4:where u using ollama and how did you make it hear you .

l1br3n <3 :

Guys, im making my own jarvis and have some questions. I use Gemini Api for conversations/asking, but it have a problem( i have only 20 tokens per day. No meter if i send to Gemini Media or text. Did u know what should i use to have more tokens?(maybe other Api or LLM)

samuel n :

I love your videos bro

beatricelock :

love your Jarvis!!

Wael Ali :

the response speed and tts are remarkable , because with supertonic cannot get this speed

Drye :

when does this release to open source?

AGRO_zachodniopomorskie :

Would you make an Iron Man Mark 3 armor?

ILT Blaz1kk :

first

rileyduckwort22 :

When are u releasing this I want a go 🤣🤣

레한_요루 :

Can we use it

𝔏0𝔏0.𝔈𝔇!𝔗𝔖 :

is this windows or mac?

𝕄𝔸7™ :

He has the blue print in digital contract on the cyber space.. 😇

༒ ᴵᵐᵖʀɛɮօʀռ༒ :

wish I can get to meet you someday 🥺

Waldo :

https://github.com/open-jarvis/OpenJarvis?tab=readme-ov-file

A-Solo :

I’m always interested in J.A.R.V.I.S.😁😁😁😁

Rickyboun :

Cool

Easton😮‍💨 :

Tuff

atSarmientoo :

me gustan tus videos, quisiera replicarlo en mi PC también para mis trabajos personales...

HoodedGamer :

I WANT THIS SO BADLY 🥰🥰🥰🥰

Sveinn Jónsson :

Mauritz Maritz :

👏👏👏

💸Pindan Alay💵 :

🥰🥰🥰

Columbus Georgia Eats | Foodie :

So I’m building one called avatar and it’s going well. I’m working on the harness now. But running into an issue. It seems to be giving me issues with understanding what I’m saying. Using a laptop for now to test, but it seems like it’s always picking up background noise, mishearing words. I’m using gpt5.5 as the brain. Here is the setup. • Hearing/STT: faster_whisper / WhisperModel • Speech detection/VAD: webrtcvad • Mic/audio I/O: sounddevice • Mic stream: sd.RawInputStream • Speaker stream: sd.OutputStream • Current STT model default: distil-large-v3 • Input device: 15 Realtek WASAPI mic • Output device: 10 Realtek DirectSound speakers • VAD aggressiveness: any Ideas on a better pipeline to use for this part?