I cant use ai agents with gpt audio models

##Describe the problem/error/question##

I’m trying to use the AI Agent node in n8n, and I have selected an audio-enabled model in the OpenAI Chat Model node. However, I keep getting errors when trying to provide the audio file in the correct format.

I do not want to transcribe the audio into text and then use a chat-based approach.

Instead, I want to directly send the audio file to OpenAI’s GPT model for processing.

##What is the error message (if any)?##

Bad request - please check your parameters
This model requires that either input content or output modality contain audio.

##Please share your workflow##

Share the output returned by the last node

I’m trying to send the binary data using $input.item.binary.data.data, but the model does not recognize it as valid audio input and throws an error.

What input field should I use, and how should I format it properly?

Information on your n8n setup

n8n version: [last version]

Database (default: SQLite): [postgres]

• **Running n8n via Docker

Operating system: [Linux but I dont know which version]

I have not tested this personally. But you may want to use the openai node for this and not the agent node.