ChatGPT to roll out text-to-video feature soon


ChatGPT’s newly introduced advanced ability can turn text into video and the feature will be launching soon allowing for the possibility of text-to-video generation.

The new ability will be launched as part of GPT-4, a new “more powerful and versatile” update of GPT 3.5, which as per tech website Stuff is ChatGPT’s large language model.

The update was announced by Andreas Braun, Chief Technology Officer of Microsoft Germany, at the ‘AI in Focus — Digital Kickoff’ held on March 4. Microsoft is the largest investor in OpenAI, the company behind the popular Chatbot.

As per reports, the model is expected to be multimodal, i.e., it will include capabilities beyond just text, and will include images and videos.

“We will introduce GPT-4 next week; there we will have multimodal models that will offer completely different possibilities — for example, videos,” said Braun.

Due to its multimodal capabilities, the chat-based AI could possibly be able to translate text into images, video and even sound, reports ZD Net.

ChatGPT runs on a language model architecture called Generative Pre-trained Transformer, popularly known as GPT. The current GPT-3 and 3.5 versions limit the chatbot to text output.

This text-to-video generator model isn’t all that revolutionary a concept. Tech giants like Google and Meta already offer models with the service.

Comments are closed.