Support all audio response formats

[besidev]

The current API should support all audio response formats currently offered by OpenAI Audio endpoint:

• The format of the transcript output, in one of these options: json, text, srt, verbose_json, or vtt.
• The format of the translation output, in one of these options: json, text, srt, verbose_json, or vtt.

[besidev]

Hello @TheoKanning,

If help is needed to maintain the project, please let me know, my team can help.