Query the supported audio-to-text models

{
    "success": true,
    "model_list": [
        {
            "model": "whisper-1",
            "provider": "openai",
            "response_format_list": [
                "json",
                "text",
                "srt",
                "vtt",
                "verbose_json"
            ]
        },
        {
            "model": "gpt-4o-transcribe",
            "provider": "openai",
            "response_format_list": [
                "json"
            ]
        },
        {
            "model": "gpt-4o-mini-transcribe",
            "provider": "openai",
            "response_format_list": [
                "json"
            ]
        },
        {
            "model": "gpt-4o-transcribe-diarize",
            "provider": "openai",
            "response_format_list": [
                "json",
                "text",
                "diarized_json"
            ]
        },
        {
            "model": "recognize",
            "provider": "doubao",
            "response_format_list": [
                "json",
                "text",
                "srt",
                "vtt",
                "verbose_json"
            ]
        },
        {
            "model": "scribe_v1_experimental",
            "provider": "elevenlabs",
            "response_format_list": [
                "json",
                "text",
                "srt",
                "vtt",
                "verbose_json"
            ]
        },
        {
            "model": "scribe_v1",
            "provider": "elevenlabs",
            "response_format_list": [
                "json",
                "text",
                "srt",
                "vtt",
                "verbose_json"
            ]
        },
        {
            "model": "sensevoice",
            "provider": "siliconflow",
            "response_format_list": [
                "json",
                "text"
            ]
        }
    ]
}