The error message says "Fix validation errors to publish" but im not sure where that validation error is at. there is no error indication somwhere to follow. this only happends when i try to publish the gpt-realtime clusters. https://cdn.discordapp.com/attachments/1446787121099706451/1446787121569337395/Screenshot_1.png?ex=694075c1&is=693f2441&hm=f6f344753293837d4f2088629c748537ec920659e145292008a52cd601411e1a&

Hi there, Thank you for your message. Our team is currently out of the office. We operate Monday through Friday, from 9:00 AM to 8:00 PM Pacific Standard Time (PST). We’ll get back to you as soon as possible during our normal business hours. If your message is urgent, please mark it accordingly or include “URGENT” in the subject line, and we’ll do our best to respond promptly. Warm regards, Vapi Customer Support Team

It looks like the model name "gpt-40-mini-realtime-preview-2024-12-17" has a typo—replace the zero with a lowercase "o" so it reads "gpt-4o-mini-realtime-preview-2024-12-17". Update your configuration as follows:

json
"model": "gpt-4o-mini-realtime-preview-2024-12-17"

This should resolve the validation error when publishing your OpenAI realtime model. For more details, see the official documentation. Source: - [OpenAI Realtime Documentation](https://docs.vapi.ai/openai-realtime)

never mind i think i solved it

Glad you were able to get this resolved. If anything else comes up or you need further assistance, we’re here to help.

I am having a similar problem: https://cdn.discordapp.com/attachments/1446787121099706451/1459163173218291722/image.png?ex=6962471a&is=6960f59a&hm=30e0d77cd2421af45700b2c93bf9ec228caae9cb74484520b2688d612b36a455&

make sure to also select the model for the OpenAI provider voice

So if I want to use Realtime with a german setup, of transcriber, ist this possible?

yes it should be possible as long as you are using gpt-4o-transcribe