Overview
Explore the latest advancements in OpenAI's text-to-speech (TTS) and GPT-4V models in this 15-minute video tutorial. Discover innovative applications of these technologies, including generating image descriptions and creating audio content. Learn how to produce voiceovers for images and videos using a combination of TTS and GPT-4V. Follow along as the presenter demonstrates practical examples and showcases novel ways developers have been utilizing these powerful tools. Gain insights into the potential of AI-driven content creation and enhance your understanding of cutting-edge language and vision models.
Syllabus
Intro
Using TTS to create audio
Using GPT4V to describe images
Using TTS & GPT4V for Video voiceovers
Conclusion
Taught by
Ian Wootten