Stream Speech

import asyncio
import websockets
import json
import base64

async def stream_tts():
    uri = "wss://api.kugelaudio.com/ws/tts?api_key=YOUR_API_KEY"
    audio_chunks = []

    async with websockets.connect(uri) as ws:
        # Send request
        await ws.send(json.dumps({
            "text": "Hello, this is streaming audio.",
            "model_id": "kugel-3",
            "voice_id": 1071,
            "cfg_scale": 2.0,
        }))

        # Receive chunks
        async for message in ws:
            data = json.loads(message)

            if "error" in data:
                # Error frames end the request without a final; the socket stays open
                raise RuntimeError(data)

            if "audio" in data:
                audio_chunks.append(base64.b64decode(data["audio"]))
                print(f"Chunk {data['idx']}: {data['samples']} samples")

            if data.get("final"):
                print(f"Complete: {data['dur_ms']}ms audio in {data['gen_ms']}ms")
                usage = data.get("usage", {})
                # cost_cents is the actual charge (EUR cents); None if unavailable
                print(f"Usage: {usage.get('audio_seconds')}s, {usage.get('cost_cents')} ct")
                break

asyncio.run(stream_tts())

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

function streamTTS(text, voiceId = 1071) {
  return new Promise((resolve, reject) => {
    const ws = new WebSocket(`${WS_URL}/ws/tts?api_key=${API_KEY}`);
    const audioChunks = [];

    ws.onopen = () => {
      ws.send(JSON.stringify({
        text,
        model_id: 'kugel-3',
        voice_id: voiceId,
        cfg_scale: 2.0,
      }));
    };

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

      if (data.error) { reject(new Error(data.error)); return; }

      if (data.audio) {
        const binary = atob(data.audio);
        const bytes = new Uint8Array(binary.length);
        for (let i = 0; i < binary.length; i++) bytes[i] = binary.charCodeAt(i);
        audioChunks.push(bytes);
        console.log(`Chunk ${data.idx}: ${data.samples} samples`);
      }

      if (data.final) {
        console.log(`Complete: ${data.dur_ms}ms audio in ${data.gen_ms}ms`);
        // Per-request usage: audio time + actual charge (EUR cents, null if unavailable)
        console.log('Usage:', data.usage);
        ws.close();
        resolve(audioChunks);
      }
    };

    ws.onerror = () => reject(new Error('WebSocket error'));
  });
}

streamTTS('Hello, this is streaming audio.')
  .then(chunks => console.log(`Received ${chunks.length} chunks`))
  .catch(console.error);

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

# Once connected, send:
> {"text": "Hello, this is streaming audio.", "model_id": "kugel-3", "voice_id": 1071, "cfg_scale": 2.0}