Multi-context streaming

import asyncio
import websockets
import json
import base64

async def multi_speaker_demo():
    async with websockets.connect(
        "wss://api.kugelaudio.com/ws/tts/multi?api_key=YOUR_API_KEY"
    ) as ws:
        # The first non-empty text for an ID creates its context.
        await ws.send(json.dumps({
            "text": "The story begins.",
            "context_id": "narrator",
            "voice_settings": {"voice_id": 1071},
            "flush": True,
        }))

        await ws.send(json.dumps({
            "text": "Hello, I'm the main character!",
            "context_id": "character",
            "voice_settings": {"voice_id": 1072},
            "flush": True,
        }))

        # Gracefully drain and close both contexts.
        await ws.send(json.dumps({"close_context": True, "context_id": "narrator"}))
        await ws.send(json.dumps({"close_context": True, "context_id": "character"}))

        # Receive audio from both contexts
        closed = set()
        async for message in ws:
            data = json.loads(message)

            if "audio" in data:
                context_id = data["context_id"]
                audio_bytes = base64.b64decode(data["audio"])
                play_audio(context_id, audio_bytes)

            if data.get("context_closed"):
                # Per-context usage for this conversation: audio time + charge
                print(f"[{data['context_id']}] usage: {data.get('usage')}")
                closed.add(data["context_id"])
                if len(closed) == 2:
                    await ws.send(json.dumps({"close_socket": True}))

            if data.get("session_closed"):
                break

asyncio.run(multi_speaker_demo())

const ws = new WebSocket('wss://api.kugelaudio.com/ws/tts/multi?api_key=YOUR_API_KEY');

const audioQueues = new Map();
const closedContexts = new Set();

ws.onopen = () => {
  // The first non-empty text for an ID creates its context.
  ws.send(JSON.stringify({
    text: 'Once upon a time...',
    context_id: 'narrator',
    voice_settings: { voice_id: 1071 },
    flush: true,
  }));

  ws.send(JSON.stringify({
    text: 'That sounds like the beginning of a story!',
    context_id: 'character',
    voice_settings: { voice_id: 1072 },
    flush: true,
  }));

  ws.send(JSON.stringify({ close_context: true, context_id: 'narrator' }));
  ws.send(JSON.stringify({ close_context: true, context_id: 'character' }));
};

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

  if (data.audio) {
    const contextId = 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(contextId)) audioQueues.set(contextId, []);
    audioQueues.get(contextId).push(bytes);
  }

  if (data.chunk_complete) {
    console.log(`Context ${data.context_id} chunk done`);
  }

  if (data.context_closed) {
    // Per-context usage for this conversation: audio time + charge
    console.log(`[${data.context_id}] usage:`, data.usage);
    closedContexts.add(data.context_id);
    if (closedContexts.size === 2) {
      ws.send(JSON.stringify({ close_socket: true }));
    }
  }

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

# Multi-context streaming requires a WebSocket client.
# Install websocat: https://github.com/vi/websocat

# Connect and send JSON messages interactively:
websocat "wss://api.kugelaudio.com/ws/tts/multi?api_key=$KUGELAUDIO_API_KEY"

# Then type each message and press Enter:
{"text": "The story begins.", "context_id": "narrator", "voice_settings": {"voice_id": 1071}, "flush": true}
{"text": "Hello, I'm the main character!", "context_id": "character", "voice_settings": {"voice_id": 1072}, "flush": true}
{"close_context": true, "context_id": "narrator"}
{"close_context": true, "context_id": "character"}
{"close_socket": true}