AZURE_OPENAI_AUDIO_API_KEY=your_realtime_api_key
AZURE_OPENAI_AUDIO_ENDPOINT=https://your-resource.cognitiveservices.azure.com
AZURE_OPENAI_AUDIO_DEPLOYMENT=gpt-realtime-mini

from openai import AsyncOpenAI
import base64

# Convert HTTPS endpoint to WebSocket URL
ws_url = endpoint.replace("https://", "wss://") + "/openai/v1"

client = AsyncOpenAI(
    websocket_base_url=ws_url,
    api_key=api_key
)

audio_chunks = []
transcript_parts = []

async with client.realtime.connect(model="gpt-realtime-mini") as conn:
    # Configure for audio-only output
    await conn.session.update(session={
        "output_modalities": ["audio"],
        "instructions": "You are a narrator. Speak naturally."
    })
    
    # Send text to narrate
    await conn.conversation.item.create(item={
        "type": "message",
        "role": "user",
        "content": [{"type": "input_text", "text": prompt}]
    })
    
    await conn.response.create()
    
    # Collect streaming events
    async for event in conn:
        if event.type == "response.output_audio.delta":
            audio_chunks.append(base64.b64decode(event.delta))
        elif event.type == "response.output_audio_transcript.delta":
            transcript_parts.append(event.delta)
        elif event.type == "response.done":
            break

# Convert PCM to WAV (see scripts/pcm_to_wav.py)
pcm_audio = b''.join(audio_chunks)
wav_audio = pcm_to_wav(pcm_audio, sample_rate=24000)

// Convert base64 WAV to playable blob
const base64ToBlob = (base64, mimeType) => {
  const bytes = atob(base64);
  const arr = new Uint8Array(bytes.length);
  for (let i = 0; i < bytes.length; i++) arr[i] = bytes.charCodeAt(i);
  return new Blob([arr], { type: mimeType });
};

const audioBlob = base64ToBlob(response.audio_data, 'audio/wav');
const audioUrl = URL.createObjectURL(audioBlob);
new Audio(audioUrl).play();