import asyncio
import websockets
import json
import base64

OPENAI_API_KEY = "sk-..."

async def voice_session():
    url = "wss://api.openai.com/v1/realtime?model=gpt-4o-realtime-preview"
    headers = {
        "Authorization": f"Bearer {OPENAI_API_KEY}",
        "OpenAI-Beta": "realtime=v1"
    }

    async with websockets.connect(url, extra_headers=headers) as ws:
        # Configure session
        await ws.send(json.dumps({
            "type": "session.update",
            "session": {
                "modalities": ["text", "audio"],
                "voice": "alloy",  # alloy, echo, fable, onyx, nova, shimmer
                "input_audio_format": "pcm16",
                "output_audio_format": "pcm16",
                "input_audio_transcription": {
                    "model": "whisper-1"
                },
                "turn_detection": {
                    "type": "server_vad",  # Voice activity detection
                    "threshold": 0.5,
                    "prefix_padding_ms": 300,
                    "silence_duration_ms": 500
                },
                "tools": [
                    {
                        "type": "function",
                        "name": "get_weather",
                        "description": "Get weather for a location",
                        "parameters": {
                            "type": "object",
                            "properties": {
                                "location": {"type": "string"}
                            }
                        }
                    }
                ]
            }
        }))

        # Send audio (PCM16, 24kHz, mono)
        async def send_audio(audio_bytes):
            await ws.send(json.dumps({
                "type": "input_audio_buffer.append",
                "audio": base64.b64encode(audio_bytes).decode()
            }))

        # Receive events
        async for message in ws:
            event = json.loads(message)

            if event["type"] == "resp

# Vapi provides hosted voice agents with webhooks

from flask import Flask, request, jsonify
import vapi

app = Flask(__name__)
client = vapi.Vapi(api_key="...")

# Create an assistant
assistant = client.assistants.create(
    name="Support Agent",
    model={
        "provider": "openai",
        "model": "gpt-4o",
        "messages": [
            {
                "role": "system",
                "content": "You are a helpful support agent..."
            }
        ]
    },
    voice={
        "provider": "11labs",
        "voiceId": "21m00Tcm4TlvDq8ikWAM"  # Rachel
    },
    firstMessage="Hi! How can I help you today?",
    transcriber={
        "provider": "deepgram",
        "model": "nova-2"
    }
)

# Webhook for conversation events
@app.route("/vapi/webhook", methods=["POST"])
def vapi_webhook():
    event = request.json

    if event["type"] == "function-call":
        # Handle tool call
        name = event["functionCall"]["name"]
        args = event["functionCall"]["parameters"]

        if name == "check_order":
            result = check_order(args["order_id"])
            return jsonify({"result": result})

    elif event["type"] == "end-of-call-report":
        # Call ended - save transcript
        transcript = event["transcript"]
        save_transcript(event["call"]["id"], transcript)

    return jsonify({"ok": True})

# Start outbound call
call = client.calls.create(
    assistant_id=assistant.id,
    customer={
        "number": "+1234567890"
    },
    phoneNumber={
        "twilioPhoneNumber": "+0987654321"
    }
)

# Or create web call
web_call = client.calls.create(
    assistant_id=assistant.id,
    type="web"
)
# Returns URL for WebRTC connection

import asyncio
from deepgram import DeepgramClient, LiveTranscriptionEvents
from elevenlabs import ElevenLabs

# Deepgram real-time transcription
deepgram = DeepgramClient(ap