Text to Speech

curl -s https://zyraxonai.lovable.app/api/public/tts \
  -H "Content-Type: application/json" \
  -d '{"text":"Hello from ZYRAXON.","locale":"en"}' \
  -o answer.mp3

# Play it
ffplay -nodisp -autoexit answer.mp3    # macOS: afplay   Windows: start

# Bengali
curl -s https://zyraxonai.lovable.app/api/public/tts -H "Content-Type: application/json" \
  -d '{"text":"আমি একটি ZYRAXON মডেল।","locale":"bn"}' -o bn.mp3

# Hindi, naming the voice exactly
curl -s https://zyraxonai.lovable.app/api/public/tts -H "Content-Type: application/json" \
  -d '{"text":"नमस्ते","voice":"hi-IN-SwaraNeural"}' -o hi.mp3

# Arabic
curl -s https://zyraxonai.lovable.app/api/public/tts -H "Content-Type: application/json" \
  -d '{"text":"مرحبا","locale":"ar"}' -o ar.mp3

curl -s https://zyraxonai.lovable.app/api/public/tts/voices | jq '{count, languages: (.languages|length)}'
# {"count": 322, "languages": 75}

# Every Bengali voice
curl -s https://zyraxonai.lovable.app/api/public/tts/voices | jq -r '.data[] | select(.locale | startswith("bn")) | .name'
# bn-BD-NabanitaNeural
# bn-BD-PradeepNeural
# bn-IN-BashkarNeural
# bn-IN-TanishaaNeural

# Every language the catalogue covers
curl -s https://zyraxonai.lovable.app/api/public/tts/voices | jq -r '.locales[]' | sort -u | head -20

// Speak an answer while it is still being written.
// A reply arrives token by token; feed the growing text and speak each
// completed sentence as it appears. The first sentence is heard while the
// model is still writing the second.
const TTS = "https://zyraxonai.lovable.app/api/public/tts";

const queue: string[] = [];
let buffer = "";
let speaking = false;

async function speak(text: string) {
  const res = await fetch(TTS, {
    method: "POST",
    headers: { "Content-Type": "application/json" },
    body: JSON.stringify({ text }),   // the locale is detected from the text
  });
  const audio = new Audio(URL.createObjectURL(await res.blob()));
  await new Promise<void>((done) => {
    audio.onended = () => done();
    audio.onerror = () => done();
    audio.play();
  });
}

async function pump() {
  if (speaking) return;
  speaking = true;
  while (queue.length) await speak(queue.shift()!);
  speaking = false;
}

// Call this on every streamed token.
function feed(chunk: string) {
  buffer += chunk;
  // Cut after each sentence terminator, including the Bengali danda.
  let at = -1;
  for (let i = 0; i < buffer.length; i++) if (/[.!?।॥]/.test(buffer[i]!)) at = i;
  if (at >= 0) {
    queue.push(buffer.slice(0, at + 1).trim());
    buffer = buffer.slice(at + 1).trimStart();
    void pump();
  }
}

// When the answer ends, speak whatever is left.
function finish() {
  if (buffer.trim()) queue.push(buffer.trim());
  buffer = "";
  void pump();
}