ws://api.60db.ai/ws/tts?apiKey=sk_live_your_api_key
ws://api.60db.ai/ws/tts?token=eyJ...&workspace_id=24

Client                                  Server
  |                                       |
  |─── create_context ──────────────────▶ |
  |◀── context_created ─────────────────  |
  |                                       |
  |─── send_text ───────────────────────▶ |
  |─── send_text ───────────────────────▶ |
  |─── flush_context ───────────────────▶ |
  |◀── audio_chunk #1 ──────────────────  |
  |◀── audio_chunk #2 ──────────────────  |
  |◀── audio_chunk #N ──────────────────  |
  |◀── flush_completed ─────────────────  |
  |                                       |
  |─── close_context ───────────────────▶ |
  |◀── context_closed ──────────────────  |
  |          (connection closes)          |

const ws = new WebSocket('ws://api.60db.ai/ws/tts?apiKey=sk_live_your_key');

{"send_text": {"context_id": "ctx-1", "text": "Hello, "}}
{"send_text": {"context_id": "ctx-1", "text": "how are you "}}
{"send_text": {"context_id": "ctx-1", "text": "doing today?"}}

let audioCtx;
let nextPlayTime = 0;

function onAudioChunk(base64Audio, sampleRate) {
  const binary = atob(base64Audio);
  const bytes = new Uint8Array(binary.length);
  for (let i = 0; i < binary.length; i++) bytes[i] = binary.charCodeAt(i);

  // Decode PCM int16 LE → Float32
  const int16 = new Int16Array(bytes.buffer);
  const float32 = new Float32Array(int16.length);
  for (let i = 0; i < int16.length; i++) float32[i] = int16[i] / 32768;

  if (!audioCtx) audioCtx = new AudioContext({ sampleRate });
  const buf = audioCtx.createBuffer(1, float32.length, sampleRate);
  buf.getChannelData(0).set(float32);
  const source = audioCtx.createBufferSource();
  source.buffer = buf;
  source.connect(audioCtx.destination);

  const now = audioCtx.currentTime;
  // First chunk: 150ms pre-buffer to absorb network jitter
  // Late chunks: schedule 20ms ahead for minimal gap
  if (nextPlayTime <= now) {
    nextPlayTime = now + (nextPlayTime === 0 ? 0.15 : 0.02);
  }
  source.start(nextPlayTime);
  nextPlayTime += float32.length / sampleRate;
}

import json
import base64
import websockets

async def llm_to_tts(llm_stream, voice_id):
    API_KEY = "sk_live_your_key"
    url = f"ws://api.60db.ai/ws/tts?apiKey={API_KEY}"

    async with websockets.connect(url) as ws:
        # Wait for connection
        await ws.recv()  # connection_established

        # Create context
        await ws.send(json.dumps({
            "create_context": {
                "context_id": "llm-session",
                "voice_id": voice_id,
                "audio_config": {"audio_encoding": "MULAW", "sample_rate_hertz": 8000}
            }
        }))
        await ws.recv()  # context_created

        # Stream LLM tokens as text chunks
        async for token in llm_stream:
            await ws.send(json.dumps({
                "send_text": {"context_id": "llm-session", "text": token}
            }))

        # Flush + close when LLM is done
        await ws.send(json.dumps({
            "flush_context": {"context_id": "llm-session"}
        }))

        audio = b""
        while True:
            msg = json.loads(await ws.recv())
            if "audio_chunk" in msg:
                audio += base64.b64decode(msg["audio_chunk"]["audioContent"])
            elif "flush_completed" in msg:
                break
            elif "error" in msg:
                raise RuntimeError(msg["error"]["message"])

        await ws.send(json.dumps({
            "close_context": {"context_id": "llm-session"}
        }))
        await ws.recv()  # context_closed

        return audio

"audio_config": {
  "audio_encoding": "MULAW",
  "sample_rate_hertz": 8000
}

"audio_config": {
  "audio_encoding": "OGG_OPUS",
  "sample_rate_hertz": 24000
}

fbb75ed2-975a-40c7-9e06-38e30524a9a1

// Create once
ws.send(JSON.stringify({
  create_context: { context_id, voice_id, audio_config }
}));

// Send multiple texts
ws.send(JSON.stringify({ send_text: { context_id, text: "Hello" } }));
ws.send(JSON.stringify({ flush_context: { context_id } }));

ws.send(JSON.stringify({ send_text: { context_id, text: "World" } }));
ws.send(JSON.stringify({ flush_context: { context_id } }));

// Close when done
ws.send(JSON.stringify({ close_context: { context_id } }));

const context1 = 'ctx-1';
const context2 = 'ctx-2';

// Create both contexts
ws.send(JSON.stringify({
  create_context: {
    context_id: context1,
    voice_id: voice1,
    audio_config
  }
}));

ws.send(JSON.stringify({
  create_context: {
    context_id: context2,
    voice_id: voice2,
    audio_config
  }
}));

# Install wscat
npm install -g wscat

# Test TTS
wscat -c "ws://api.60db.ai/ws/tts?apiKey=sk_live_your_key"

{"create_context":{"context_id":"test-123","voice_id":"fbb75ed2-975a-40c7-9e06-38e30524a9a1","audio_config":{"audio_encoding":"LINEAR16","sample_rate_hertz":16000}}}
{"send_text":{"context_id":"test-123","text":"Hello"}}
{"flush_context":{"context_id":"test-123"}}