Home Artists Posts Import Register

Downloads

Content

Hey! In this tutorial, we'll go over 2 new components I developed to run OpenAI's Whisper (speech-to-text) and ChatGPT within TouchDesigner. No need to install any dependencies.

Link to Open AI: https://platform.openai.com/signup

Update:
Note the component now works with the new GPT4 & GPT-4-Turbo Model as well. 

Files

GPT-4, ChatGPT, and Whisper(speech-to-text) Plugins for TouchDesigner

Hey! In this tutorial we'll go over 2 new components I developed to run OpenAI's Whisper (speech-to-text) and GPT-4(includes multiple versions) within TouchDesigner. The components work without any setup needed, just add your OpenAI API key. I also show how to extend the functionality of the components so you can use these models in your installations. Link to the Project File is on my Patreon: https://patreon.com/tblankensmith Link to Open AI's Website: https://platform.openai.com/signup *Update* The component from this video now works with the new GPT-4 model. You need to get on OpenAI's waitlist to get access: https://openai.com/waitlist/gpt-4-api The component defaults to GPT-3.5-turbo, so it works out of the box. If you get off the waitlist you can change the model from the component parameters, which is now listed under the API key parameter on the TD component. 0:00 Overview 1:03 Shader Generation Example 4:08 Priming messages for ChatGPT | Becoming Refik Anadol 7:23 API Key setup 9:46 In Depth use of the Whisper and ChatGPT Components 12:41 Building the connection from Whisper to ChatGPT

Comments

Anonymous

This is awesome!! I use chatgpt a lot to help with python scripts. Do you have any recommendations or direction for streamlineing that approach. I saw in the video you had a script that took the response and generated a glsl script. Is that easy to change for python?

tblankensmith

Hey I just updated this to work with the new GPT-4-Turbo model as well. Yeah, I just gave it a couple of examples of what glsl code in TouchDesigner looks like. If you want to have it work with python in TD just give it examples of using python in TD

Anonymous

Really cool man, learning a bunch. Is there a way we could trigger an event based on the response ? As in, if we ask it to press 2 seperate buttons, for example for yes / no questions

Anonymous

Me too touch designer crashes every time I hit record would really appreciate a solution

Eugene Pitts

This is such amazing work - the possibilities are staggering as you play with it. I am having the same issue as Daniel and Issac where the "record audio" causes the application to crash but the prerecorded audio works just fine. I am on Windows with the latest Stable build.

Bo

I'm using a Mac, there is an error: "No such file or directory". Do you know how to solve it or show us clearly how to connect Arduino with Chat GPT APIs?