add language parameter to InputAudioTranscription

[VrenTati]

Purpose

• Added language parameter to the Python InputAudioTranscription model.
• This allows specifying the transcription language (e.g., en, sv) instead of relying only on auto-detection.

Does this introduce a breaking change?

[ ] Yes
[ х] No

Pull Request Type

What kind of change does this Pull Request introduce?

[ ] Bugfix
[ х] Feature
[ ] Code style update (formatting, local variables)
[ ] Refactoring (no functional changes, no api changes)
[ ] Documentation content changes
[ ] Other... Please describe:

How to Test

• Get the code

git clone [repo-address]
cd [repo-name]
git checkout [branch-name]
npm install

• Test the code

transcription = InputAudioTranscription(
model="whisper-1",
language="en" # Supported values are: 'af', 'ar', 'az', 'be', 'bg', 'bs', 'ca', 'cs', 'cy', 'da', 'de', 'el', 'en', 'es', 'et', 'fa', 'fi', 'fr', 'gl', 'he', 'hi', 'hr', 'hu', 'hy', 'id', 'is', 'it', 'ja', 'kk', 'kn', 'ko', 'lt', 'lv', 'mi', 'mk', 'mr', 'ms', 'ne', 'nl', 'no', 'pl', 'pt', 'ro', 'ru', 'sk', 'sl', 'sr', 'sv', 'sw', 'ta', 'th', 'tl', 'tr', 'uk', 'ur', 'vi', and 'zh'."

{
    "session": {
        "input_audio_transcription": {
            "model": "gpt-4o-transcribe",
            "language": "en"
        }
}

What to Check

Verify that the following are valid

• creating session update object

Other Information

• Based on Azure Speech Service supported languages list.
• No breaking changes introduced — default behavior remains unchanged if language is not provided.