Text to speech realtime

pocket-tts

Live Pocket TTS. WebSocket only. $0.00333 / min plus the $0.05 request fee.

Native stream: PCM16 mono 24 kHz on wss://api.pascalai.co/v1/text-to-speech/realtime.. Live price and availability are on GET /v1/models/pocket-tts.

  • Open wss://api.pascalai.co/v1/text-to-speech/realtime.
  • Send {"type":"session.update","session":{"voice":"alba"}} before the first speak.
  • The charge follows the audio, in minutes.
  • voice is Pocket only. Default alba.
  • 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.voice
Default alba
stringPocket TTS Realtime only. One of 26 speakers. Default alba. Omit on Piper and Matcha.

Example

const socket = new WebSocket(
  'wss://api.pascalai.co/v1/text-to-speech/realtime?model=pocket-tts&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: { voice: 'alba' } }));
    socket.send(JSON.stringify({
    type: 'speak',
    text: 'Keep walking toward the river.',
  }));
  }
};
// binary Int16 PCM16 frames, then response.done