Multi-Context WebSocket API

import asyncio
import websockets
import json
import base64

async def multi_speaker():
    uri = "wss://api.kugelaudio.com/ws/tts/multi?api_key=YOUR_API_KEY"

    async with websockets.connect(uri) as ws:
        # Create narrator context
        await ws.send(json.dumps({
            "text": "",
            "context_id": "narrator",
            "voice_settings": {"voice_id": 1071},
        }))

        # Create character context
        await ws.send(json.dumps({
            "text": "",
            "context_id": "character",
            "voice_settings": {"voice_id": 1072},
        }))

        # Send text to different speakers
        await ws.send(json.dumps({
            "text": "The story begins.",
            "context_id": "narrator",
            "flush": True,
        }))

        await ws.send(json.dumps({
            "text": "Hello, I'm the main character!",
            "context_id": "character",
            "flush": True,
        }))

        # Receive audio from both contexts. After both flushed turns reach
        # their final frame, close the connection gracefully.
        completed = set()
        async for message in ws:
            data = json.loads(message)

            if "audio" in data:
                ctx = data["context_id"]
                audio_bytes = base64.b64decode(data["audio"])
                print(f"[{ctx}] Chunk {data['idx']}: {len(audio_bytes)} bytes")

            if data.get("context_closed"):
                usage = data.get("usage", {})
                # Per-context (per-conversation) usage: audio time + charge (EUR cents)
                print(f"[{data['context_id']}] usage: {usage.get('audio_seconds')}s, "
                      f"{usage.get('cost_cents')} ct")

            if data.get("final"):
                completed.add(data["context_id"])
                if completed == {"narrator", "character"}:
                    await ws.send(json.dumps({"close_socket": True}))

            if data.get("session_closed"):
                break

asyncio.run(multi_speaker())

const API_KEY = 'YOUR_API_KEY';
const WS_URL = 'wss://api.kugelaudio.com';

const ws = new WebSocket(`${WS_URL}/ws/tts/multi?api_key=${API_KEY}`);
const audioQueues = new Map();
const completed = new Set();

ws.onopen = () => {
  // Create narrator context
  ws.send(JSON.stringify({
    text: '',
    context_id: 'narrator',
    voice_settings: { voice_id: 1071 },
  }));

  // Create character context
  ws.send(JSON.stringify({
    text: '',
    context_id: 'character',
    voice_settings: { voice_id: 1072 },
  }));

  // Send text to different speakers
  ws.send(JSON.stringify({
    text: 'The story begins.',
    context_id: 'narrator',
    flush: true,
  }));

  ws.send(JSON.stringify({
    text: 'Hello, I\'m the main character!',
    context_id: 'character',
    flush: true,
  }));
};

ws.onmessage = (event) => {
  const data = JSON.parse(event.data);

  if (data.audio) {
    const ctx = data.context_id;
    const binary = atob(data.audio);
    const bytes = new Uint8Array(binary.length);
    for (let i = 0; i < binary.length; i++) bytes[i] = binary.charCodeAt(i);

    if (!audioQueues.has(ctx)) audioQueues.set(ctx, []);
    audioQueues.get(ctx).push(bytes);
    console.log(`[${ctx}] Chunk ${data.idx}: ${bytes.length} bytes`);
  }

  if (data.context_closed) {
    // Per-context (per-conversation) usage: audio time + actual charge
    console.log(`[${data.context_id}] usage:`, data.usage);
  }

  if (data.final) {
    completed.add(data.context_id);
    if (completed.size === 2) ws.send(JSON.stringify({ close_socket: true }));
  }

  if (data.session_closed) {
    ws.close();
  }
};

# Install wscat: npm install -g wscat
wscat -c "wss://api.kugelaudio.com/ws/tts/multi?api_key=YOUR_API_KEY"

# Create narrator context
> {"text": "", "context_id": "narrator", "voice_settings": {"voice_id": 1071}}

# Create character context
> {"text": "", "context_id": "character", "voice_settings": {"voice_id": 1072}}

# Send text to narrator
> {"text": "The story begins.", "context_id": "narrator", "flush": true}

# Send text to character
> {"text": "Hello, I'm the main character!", "context_id": "character", "flush": true}

# Close all contexts
> {"close_socket": true}