Text to speech realtime

matcha-en-ljspeech

Live Matcha LJSpeech. WebSocket only. $0.00333 / min plus the $0.05 request fee.

Native stream: PCM16 mono 22.05 kHz on wss://api.pascalai.co/v1/text-to-speech/realtime.. Live price and availability are on GET /v1/models/matcha-en-ljspeech.

  • Open wss://api.pascalai.co/v1/text-to-speech/realtime.
  • Send session.update before the first speak, then {"type":"speak","text":"…"}. Binary PCM16 follows.
  • The charge follows the audio, in minutes.
  • A browser sends the API key as api_key on the query string.

Parameters

FieldTypeDescription
speak.textRequiredstringThe words to speak. Same field on every live TTS model.
session.speed
Default 1
numberPiper and Matcha only. 0.5 to 2. Default 1. Omit on Pocket.

Example

const socket = new WebSocket(
  'wss://api.pascalai.co/v1/text-to-speech/realtime?model=matcha-en-ljspeech&api_key=' + key
);
socket.binaryType = 'arraybuffer';
socket.onmessage = (event) => {
  if (typeof event.data !== 'string') return;
  const payload = JSON.parse(event.data);
  if (payload.type === 'session.created') {
    socket.send(JSON.stringify({ type: 'session.update', session: { speed: 1 } }));
    socket.send(JSON.stringify({
    type: 'speak',
    text: 'Keep walking toward the river.',
  }));
  }
};
// binary Int16 PCM16 frames, then response.done