Realtime API input audio tokens increase even if text is entered.

[ivan-luchkin-u]

I have started a topic on this very issue earlier

Realtime API re-consuming it's own output audio as input audio

I have built my own client which does not send any audio to the API, but the “audio” modality is still enabled so that the model can respond with audio. I have also implemented something to keep track of all the tokens (i/o, cached etc.) so that I can calculate the price. To my surprise, I have found out that audio_tokens are not zero starting from the second model response, which I assume can only mean that the model feeds on the audio tokens it generated previously. Can someone please elabor…

This is expected behavior. The model needs to consume output audio tokens because they are a part of the conversation history.