Voice APIs

import asyncio
import json
import os
import websockets

async def voice_agent():
    async with websockets.connect(
        "wss://api.x.ai/v1/realtime",
        additional_headers={"Authorization": f"Bearer {os.environ['XAI_API_KEY']}"}
    ) as ws:
        # Configure voice and enable tools
        await ws.send(json.dumps({
            "type": "session.update",
            "session": {
                "voice": "Eve",
                "instructions": "You are a helpful customer support agent.",
                "turn_detection": {"type": "server_vad"},
                "tools": [{"type": "web_search"}]
            }
        }))
        
        # Stream audio and receive responses
        async for message in ws:
            event = json.loads(message)
            if event["type"] == "response.output_audio.delta":
                # Play audio: base64.b64decode(event["delta"])
                pass

asyncio.run(voice_agent())

import os
import requests

response = requests.post(
    "https://api.x.ai/v1/tts",
    headers={
        "Authorization": f"Bearer {os.environ['XAI_API_KEY']}",
        "Content-Type": "application/json",
    },
    json={
        "text": "Welcome to xAI. How can I help you today?",
        "voice_id": "eve",
        "language": "en",
    },
)

with open("welcome.mp3", "wb") as f:
    f.write(response.content)