What's LangChain's stance on text-to-speech integration?

[zhouzi]

I can't find any discussions about OpenAI's recent text-to-speech addition.

I am wondering if it would make sense for LangChain to support it somehow?

[seb7wake]

I've also been looking into how to do this, and need a way to add X seconds of silence between sentences. Would love to avoid pinging their TTS API 10+ times. Let me know if you find anything valuable!