Has anyone used the GPT4o multimodal feature announced by OpenAI?

Has anyone tried new gpt4o multidmodal features from the openai demo? Or is it that the feature hasn’t been released to anyone yet?

1 Like

I think that it’s not available yet, maybe in a few weeks.

yep not available but I would suppose it is a similar API as whisper (if you’re going to do audio inputs)