I have tried this:
const client = new RealtimeClient({
apiKey: process.env.OPENAI_API_KEY,
model: ‘gpt-4o-mini-realtime-preview-2024-12-17’,
});
and this:
client.updateSession({
model: ‘gpt-4o-mini-realtime-preview-2024-12-17’,
instructions: ‘Provide concise and accurate responses.’,
voice: ‘coral’, // Change to another voice like ‘nova’ if needed
response_mode: ‘audio’,
input_audio_transcription: { model: ‘whisper-1’ },
});
it keeps defaulting to the older 4o model.
what am i doing wrong?