Realtime API: Did anybody managed to provide previous conversation transcript history while keeping audio answers?

[samiy8030]

I have the same issue, did you find a solution ?

There is currently a little bit of a workaround. It’s not prod-ready, but it works for testing. Hoping OpenAI fixes this soon.

How can I switch from text generation to audio generation?

Hi everyone! I want to continue a previous text-only conversation with audio in the real-time API. To enable this, I create a session with text + audio modalities in the realtime API and then inject the previous text messages using conversation.item.create events, where each item has the text / input_text of the message sent by the assistant / user: Assistant message: {"event_id":"...","type":"conversation.item.create","item":{"id":"...","type":"message","status":"completed","role":"assistant…