feat: support gpt-audio

[WqyJh]

OpenAI has released a new model gpt-4o-audio-preview which is an end-to-end model for audio input/output. It can be used by chat completion api.

Reference:

• https://platform.openai.com/docs/guides/audio
• https://platform.openai.com/docs/api-reference/chat/create

[sashabaranov]

@WqyJh thank you for the PR! Please the latest changes from master here, so the CI will pass

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 99.61%. Comparing base (5d7a276) to head (7ed083f).

Additional details and impacted files

@@            Coverage Diff             @@
##           master     #895      +/-   ##
==========================================
+ Coverage   99.59%   99.61%   +0.01%     
==========================================
  Files          34       34              
  Lines        2209     1801     -408     
==========================================
- Hits         2200     1794     -406     
+ Misses          6        4       -2     
  Partials        3        3              

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[WqyJh]

Fixed @sashabaranov

[WqyJh]

Hi, @sashabaranov. Would you please help reviewing the code.

[WqyJh]

Hi, @sashabaranov, the code has been rebased onto latest master branch. Could you please assist with merging it? Thank you!

[He-hongjun]

Please resolve the merge conflict, and I'm looking forward to having it merged for use as soon as possible. Thanks for your c contribute.

[He-hongjun]

Hi, @sashabaranov, the code has been rebased onto latest master branch. Could you please assist with merging it? Thank you!

conflicts need to resolve, please take a look, thank

[HaraldNordgren]

@WqyJh @sashabaranov Can we try to get this merged as a step toward introducing Realtime API here?

[WqyJh]

@sashabaranov hi, please help merge this code to support the following models.

	GPTAudio                      = "gpt-audio"
	GPTAudio20250828              = "gpt-audio-2025-08-28"
	GPTAudioMini                  = "gpt-audio-mini"
	GPTAudioMini20251006          = "gpt-audio-mini-2025-10-06"
	GPT4oAudioPreview             = "gpt-4o-audio-preview"
	GPT4oAudioPreview20241001     = "gpt-4o-audio-preview-2024-10-01"
	GPT4oAudioPreview20241217     = "gpt-4o-audio-preview-2024-12-17"
	GPT4oAudioPreview20250603     = "gpt-4o-audio-preview-2025-06-03"
	GPT4oMiniAudioPreview         = "gpt-4o-mini-audio-preview"
	GPT4oMiniAudioPreview20241217 = "gpt-4o-mini-audio-preview-2024-12-17"