Response format for OpenAiAudioTranscriptionOptions is ignored

[NerminKarapandzic]

Please do a quick search on GitHub issues first, there might be already a duplicate issue for the one you are about to create.
If the bug is trivial, just go ahead and create the issue. Otherwise, please take a few moments and fill in the following sections:

Bug description
Response format for OpenAiAudioTranscriptionOptions is being ignored. For example, using VERBOSE_JSON and GranularityType.WORD will return simple text response.

Environment
Using spring-ai version 1.0.0-SNAPSHOT
Java version 21

Steps to reproduce
AudioTranscriptionOptions options = OpenAiAudioTranscriptionOptions.builder()
.responseFormat(TranscriptResponseFormat.VERBOSE_JSON)
.granularityType(GranularityType.WORD)
.build();

  AudioTranscriptionPrompt transcriptionRequest = new AudioTranscriptionPrompt(audioResource, options);
  AudioTranscriptionResponse response = openAiAudioTranscriptionModel.call(transcriptionRequest);

Inspect the response

Expected behavior
Response should respect the granularity and response format options.

Minimal Complete Reproducible example
Please provide a failing test or a minimal complete verifiable example that reproduces the issue.
Bug reports that are reproducible will take priority in resolution over reports that are not reproducible.