NB2L YouTube URL to Image Generation Example is Not Working

I am trying NB2L example from google documentation and it gives the error

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3.1-flash-image",
    "input": [
      {
        "type": "video",
        "uri": "https://www.youtube.com/watch?v=UTdfxFyOQTI",
        "mime_type": "video/mp4"
      },
      {
        "type": "text",
        "text": "Generate a poster image that captures the key themes of this video."
      }
    ],
    "response_format": {
      "type": "image",
      "aspect_ratio": "16:9"
    }
  }'

Error

{
“error”: {
“message”: “Audio input modality is not enabled for this model”,
“code”: “invalid_request”
}
}

Anybody able to make it work in Postman?

This model does not support video as an input, although for unknown reasons there is an error regarding audio.

Maybe this will help.

Their this documentation says different then - https://ai.google.dev/gemini-api/docs/image-generation?authuser=5#video-to-image

That changes things. I’m worried that these might be discrepancies between different versions of the Gemini product, but the manual hasn’t been updated. Because I can’t believe anyone would make such logical errors in the documentation.

Someone over there should take charge of moderating this documentation, because if that’s a maple leaf…