Tts

GET https://vas-poc.vurbo.ai/api/v1/tts/voices?language={language}

curl -X GET "https://vas-poc.vurbo.ai/api/v1/tts/voices?language=en-US" \
  -H "X-API-Key: YOUR_API_KEY"

GET https://vas-poc.vurbo.ai/api/v1/tts/voices/{voiceName}/sample

// Play directly with an Audio element
const audio = new Audio(
  'https://vas-poc.vurbo.ai/api/v1/tts/voices/en-US-JennyNeural/sample'
);
audio.play();

{
  "type": "voice-translation",
  "data": {
    "action": "start",
    "transcription_languages": ["zh-TW"],
    "translation_languages": ["en-US"],
    "realtime_translation": true,
    "type": "transcribe",
    "tts_enabled": true,
    "tts_language": "en-US",
    "tts_voice": "en-US-JennyNeural",
    "tts_mode": "sync"
  }
}

{
  "type": "voice-translation",
  "data": {
    "action": "tts_play",
    "sid": 5
  }
}

{
  "type": "voice-translation",
  "data": {
    "action": "tts_play",
    "sid": 5,
    "length": 3
  }
}

{
  "type": "voice-translation",
  "data": {
    "action": "tts_stop"
  }
}

{
  "type": "voice-translation",
  "data": {
    "action": "tts_ready",
    "sid": 1,
    "language": "en-US",
    "transcript": "你好，很高興認識你",
    "text": "Hello, nice to meet you",
    "audio": "Base64EncodedMP3...",
    "format": "mp3",
    "duration_ms": 2500,
    "boundaries": [
      {"offset_ms": 0, "duration_ms": 350, "text_offset": 0, "word_length": 5, "text": "Hello"},
      {"offset_ms": 500, "duration_ms": 250, "text_offset": 7, "word_length": 4, "text": "nice"},
      {"offset_ms": 750, "duration_ms": 200, "text_offset": 12, "word_length": 2, "text": "to"},
      {"offset_ms": 950, "duration_ms": 350, "text_offset": 15, "word_length": 4, "text": "meet"},
      {"offset_ms": 1300, "duration_ms": 300, "text_offset": 20, "word_length": 3, "text": "you"}
    ]
  }
}

ws.onmessage = (event) => {
  const msg = JSON.parse(event.data);
  if (msg.data?.action === 'tts_ready') {
    const { audio, boundaries, text } = msg.data;

    // Base64 to Blob
    const byteChars = atob(audio);
    const byteArray = new Uint8Array(byteChars.length);
    for (let i = 0; i < byteChars.length; i++) {
      byteArray[i] = byteChars.charCodeAt(i);
    }
    const blob = new Blob([byteArray], { type: 'audio/mp3' });
    const audioEl = new Audio(URL.createObjectURL(blob));
    audioEl.play();
  }
};

{
  "type": "voice-translation",
  "data": {
    "action": "tts_mode",
    "tts_mode": "async"
  }
}

GET https://vas-poc.vurbo.ai/api/v1/sse/tts/{taskId}?language={language}&sid={sid}&length={length}

connected  ->  tts_audio (repeated N times)  ->  tts_done

async function playTTS(taskId, language, apiKey, startSid = 1, length = 3) {
  const url = new URL(`https://vas-poc.vurbo.ai/api/v1/sse/tts/${taskId}`);
  url.searchParams.set('language', language);
  url.searchParams.set('sid', startSid);
  url.searchParams.set('length', length);

  const response = await fetch(url, {
    headers: { 'X-API-Key': apiKey }
  });

  const reader = response.body.getReader();
  const decoder = new TextDecoder();

  while (true) {
    const { done, value } = await reader.read();
    if (done) break;

    const events = parseSSE(decoder.decode(value));
    for (const event of events) {
      if (event.type === 'tts_audio') {
        // Play the audio and set up the karaoke effect
        const blob = base64ToBlob(event.data.audio, 'audio/mp3');
        const audio = new Audio(URL.createObjectURL(blob));
        setupKaraoke(audio, event.data.boundaries, event.data.text);
        audio.play();
      }
    }
  }
}

curl -X POST "https://vas-poc.vurbo.ai/api/v1/broadcasts" \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "transcription_language": "zh-TW",
    "translation_languages": ["en-US", "ja-JP"],
    "tts_config": {
      "en-US": {"voice": "en-US-JennyNeural", "speaking_rate": 1.0},
      "ja-JP": {"voice": "ja-JP-NanamiNeural", "speaking_rate": 1.0}
    }
  }'

{
  "type": "voice-translation",
  "data": {
    "action": "start",
    "type": "broadcast",
    "broadcast_token": "YOUR_BROADCAST_TOKEN",
    "audio_format": "pcm",
    "tts_config": {
      "en-US": {
        "voice": "en-US-JennyNeural",
        "speaking_rate": 1.0
      },
      "ja-JP": {
        "voice": "ja-JP-NanamiNeural",
        "speaking_rate": 1.0
      }
    }
  }
}

const eventSource = new EventSource(
  'https://vas-poc.vurbo.ai/broadcast/{token}/text?lang=en-US&tts=true'
);

eventSource.addEventListener('tts_ready', (e) => {
  const data = JSON.parse(e.data);
  // data.audio is the Base64-encoded MP3
  // data.boundaries is the Word Boundary array
  const blob = base64ToBlob(data.audio, 'audio/mp3');
  const audio = new Audio(URL.createObjectURL(blob));
  audio.play();
});

[
  {"offset_ms": 0,    "duration_ms": 350, "text_offset": 0,  "word_length": 5, "text": "Hello"},
  {"offset_ms": 350,  "duration_ms": 100, "text_offset": 5,  "word_length": 1, "text": ","},
  {"offset_ms": 500,  "duration_ms": 250, "text_offset": 7,  "word_length": 4, "text": "nice"},
  {"offset_ms": 750,  "duration_ms": 200, "text_offset": 12, "word_length": 2, "text": "to"},
  {"offset_ms": 950,  "duration_ms": 350, "text_offset": 15, "word_length": 4, "text": "meet"},
  {"offset_ms": 1300, "duration_ms": 300, "text_offset": 20, "word_length": 3, "text": "you"}
]

function setupKaraoke(audioElement, boundaries, text) {
  const updateHighlight = () => {
    const currentTimeMs = audioElement.currentTime * 1000;

    // Find the word currently being played
    const currentWord = boundaries.find((b, i) => {
      const nextOffset = boundaries[i + 1]?.offset_ms ?? Infinity;
      return currentTimeMs >= b.offset_ms && currentTimeMs < nextOffset;
    });

    if (currentWord) {
      // Highlight the current word
      highlightWord(text, currentWord.text_offset, currentWord.word_length);
    }
  };

  // Update the highlight position every 50ms
  const interval = setInterval(updateHighlight, 50);
  audioElement.addEventListener('ended', () => clearInterval(interval));
}

function highlightWord(text, offset, length) {
  const before = text.substring(0, offset);
  const word = text.substring(offset, offset + length);
  const after = text.substring(offset + length);

  // Update the DOM (adjust to your actual UI framework)
  document.getElementById('tts-text').innerHTML =
    `${before}<span class="highlight">${word}</span>${after}`;
}

.highlight {
  background-color: #FFD700;
  color: #000;
  padding: 2px 4px;
  border-radius: 3px;
  transition: background-color 0.1s ease;
}

{
  "type": "voice-translation",
  "data": {
    "action": "tts_mode",
    "tts_mode": "async"
  }
}

{
  "type": "voice-translation",
  "data": {
    "action": "tts_mode_changed",
    "tts_mode": "async"
  }
}

curl -X PATCH "https://vas-poc.vurbo.ai/api/v1/broadcasts/{id}" \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "tts_config": {
      "zh-TW": {"voice": "zh-TW-HsiaoChenNeural", "speaking_rate": 1.0},
      "ja-JP": {"voice": "ja-JP-NanamiNeural", "speaking_rate": 1.2}
    }
  }'

curl -X PATCH "https://vas-poc.vurbo.ai/api/v1/broadcasts/{id}" \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "tts_config": null
  }'