WebRTC Realtime API Server Error

API
, , ,
1

Hey,

I am trying to get the realtime API to work with speech, I’ve tried both the gpt-4o-realtime-preview and the gpt-4o-mini-realtime-preview

I seem to always get the same server error even though I’m pretty much just using the boilerplate code from openai’s documentation.

The webrtc connection gets successfully established, and the following series of messages is recieved at correct timings

[
  "session.created",
  "session.updated",
  "input_audio_buffer.speech_started",
  "input_audio_buffer.speech_stopped",
  "input_audio_buffer.committed",
  "conversation.item.created",
  "response.created",
  "response.done"
]

But once the request.done is recieved, it’s always an error with the following message

The server had an error while processing your request. Sorry about that! You can retry your request, or contact us through our help center at help.openai.com if the error persists. (Please include the session ID sess_BBpZz4FSSeROFszuRJmdN in your message.)

This has been like this for me today and yesterday.

I’ve tried to create a new key and I get the same thing.

Thanks in advance for any help

2

I am more then happy to share any more details to get to the bottom of this