Possible adding support for real time streaming for OpenAI Speech generation?

[simon-archer]

Hi this is a feature request/question,

According to the documentation OpenAI's Speech API supports real time streaming using chunk transfer encoding, and I was wondering if anyone is working on this, or if its even possible at all, considering the example is in python.

https://platform.openai.com/docs/guides/text-to-speech/streaming-real-time-audio