Audio Generation API crashed

Here is my code

from openai import OpenAI

client = OpenAI()

completion = client.chat.completions.create(
    model="gpt-4o-audio-preview",
    modalities=["text", "audio"],
    audio={"voice": "alloy", "format": "wav"},
    messages=[
        {
            "role": "user",
            "content": "Is a golden retriever a good family dog?"
        }
    ]
)

Here is the API response

openai.BadRequestError: Error code: 400 - {'error': {'message': "Invalid request: 'openai-internal-handleimages' and 'openai-internal-multimodal-v2' cannot both be set to true.", 'type': 'invalid_request_error', 'param': None, 'code': None}}
8 Likes

same here with “mini”, it was working on 2/23

3 Likes

Same:

Error code: 400 - {‘error’: {‘message’: “Invalid request: ‘openai-internal-handleimages’ and ‘openai-internal-multimodal-v2’ cannot both be set to true.”, ‘type’: ‘invalid_request_error’, ‘param’: None, ‘code’: None}}

I’m using gpt-4o-mini-audio-preview-2024-12-17

3 Likes

same here…
it worked on 2/21

2 Likes


same here with playground

4 Likes

Same here. Was working for me until today at 3:20 PM PT. Throwing errors ever since.

same problem. 2/23 was working good.

Same here BadRequestError: 400 Invalid request: 'openai-internal-handleimages' and 'openai-internal-multimodal-v2' cannot both be set to true.

Minimum reproducible is

            const openai = new OpenAI({
                apiKey: xxx
            });

            logger.info("Starting simple audio test (non-streaming)");

            // Create a basic non-streaming request
            const completion = await openai.chat.completions.create({
                model: "gpt-4o-mini-audio-preview",
                modalities: ["text", "audio"],
                audio: { voice: "alloy", format: "pcm16" },
                messages: [
                    {
                        role: "user",
                        content: "Is a golden retriever a good family dog? Keep your answer brief."
                    }
                ],
                max_tokens: 300,
                temperature: 0.7
            });

            // Log the complete response (truncating audio data)
            const logResponse = {...completion};

Invalid request: 'openai-internal-handleimages' and 'openai-internal-multimodal-v2' cannot both be set to true.

Chat completions, with gpt-4o-mini-audio-preview-2024-12-17, gpt-4o-mini-audio-preview, gpt-4o-audio-preview-2024-12-17, gpt-4o-audio-preview-2024-10-01… also with one “fail to get network resource”.

Days without API failure Three Zero.

1 Like

Thanks everyone for taking the time to flag this. It’s been raised with OpenAI.

Special thanks to @_j for raising visibility.

2 Likes

Thanks for reporting this! The issue has been resolved.

Please let us know if it happens again.

6 Likes