Audio input transcription issue

API
1

How can we transcribe the user input in realtime api using any different model as the currently i was using whisper - 1 which doesn’t works is there anything we can make it more better this transcriuption or we have to use the another if another how we can integrate it into our current thing .

const startSession = (userLanguage = "en") => {
    const command = {
        type: "session.update",
        session: {
            turn_detection: {
                type: "server_vad"
            },
            input_audio_transcription: {
                model: "whisper-1",
                language: userLanguage
            }
        }
    };