How to Set Up ChatGPT and Whisper API with Voice Recognition for Your AI Assistant

Example code used: github.com/JarodMica/ChatGPT-...
Project Vivy: github.com/JarodMica/Vivy
Come join the Language Journey!
Discord - / discord
TikTok - / jarodsjourney
If you found anything helpful, please consider supporting me and the content I am trying to produce!
www.buymeacoffee.com/jarodsjo... |
Hardware for my PC:
Graphics Card - amzn.to/3pcREux
CPU - amzn.to/43O66Ir
Cooler - amzn.to/3p98TwX
RAM - amzn.to/3NBAsIq
SSD Storage - amzn.to/42NgMFR
Power Supply (PSU) - amzn.to/3NBAsIq
PC Case - amzn.to/447499T
Mother Board - amzn.to/3CziMXI
Alternative prebuilds:
Corsair Vengeance i7400 - amzn.to/3p64r22
MSI MPG Velox - amzn.to/42MnJHl
Cheapest and minimum specs recommended:
Cyberpower 3060 - amzn.to/3XjtZoP

[@CrimsoniteSP]

Wow, after watching DougDoug's run on Pajama Sam, I wanted to try something similar. This is exactly what I'm looking for. Thanks so much!

[@polemic_channel]

Jarod is becoming tony stark. Vivy is more like J.A.R.V.I.S

[@Jarods_Journey]

That's the GOAL

[@polemic_channel]

@@Jarods_Journey ははははははははw

[@topsecretjony]

yeah imma need that robot girl thumbnail image

[@keshavmiglani2697]

How to use a speech recognition library to transcribe the voice coming from Google Translate's speaker instead of user voice? "# speech recognition set-up r = sr.Recognizer() mic = sr.Microphone(device_index=0) r.dynamic_energy_threshold=False r.energy_threshold = 400" Do we need to make changes here?

[@Busshanta]

Awesome , anyway to adopt it for linux?

[@Jarods_Journey]

It should work all the same for the most part, maybe some specific Linux libraries I don't know but python stays the same relatively

[@xflory26x]

I am trying to run the code step by step but after implementing the voice engine, it automatically escapes the while loop after one user input and one assistant output, would you know why that is? Is it possibly because of the runAndWait()?

[@Jarods_Journey]

Hmm, I believe I showed a while True: loop in here and it should never escape as there is no break. Did you clone the repo?

[@A-Nana]

hello jarod, i trying to run your project vivy, but i have still stuck in Listening: Done listening. Google heard: "you say" Adjusting to envionrment sound... no voice response, just text. how to make vivy respond with voice?

[@Jarods_Journey]

Any chance your running the exe versions on windows 11? Try running the python script version of it as I noticed some bugs with the exe files that I still have yet to fix

[@ranjitpatro5793]

@@Jarods_Journey Same issue for me. I am on mac os.

[@gregorykarsten7350]

Wow. Can this be adapted for real time meeting minutes generation

[@Jarods_Journey]

Absolutely, you would just need to have recorded audio and whisper could transcribe it

[@pradyumnb9731]

@@Jarods_Journey good video… is it necessary to input recorded audio? Can there be solution to write and update minutes on the go? And summarise action itmes

[@user-ur7pc6pm4i]

whisper not work ?

[@user-zy7lg7ds2z]

is all of this free? and can i give it a personality?

[@novadocnews]

I am frustrated! I cant get pass "import openai". I get a message saying import is not possible. I've searched and appearently this is because of incompatibility of python version (3.12).... Your video is 1 year old only, is it possible that in only in that time frame the python version is already so old?? I cant keep up with all this Updates when at the same time I am trying to learn how to code by using youtube tutorial.😭

[@novadocnews]

Oh, btw. Your video is amazing anyways! thank you. I wish I was able to solve this update issues on my own.