0.21.0

PlayDialog-turbo, our high-performance voice engine that provides faster response times while maintaining same audio quality, now supports ogg, mulaw and flac formats, in addition to the already supported wav and mp3 outputs.

Example:

import * as PlayHT from 'playht';

const stream = await PlayHT.stream('Get real-time responses with PlayDialog-turbo.', {
  voiceEngine: 'PlayDialog-turbo',
  voiceId: 'Celeste-PlayAI',
  language: 'english',
  outputFormat: 'mulaw',
});

0.19.1

This version introduces a new inference backend specialized in High-Fidelity Voice Clones of our PlayDialog model. If you already are using PlayDialog as model, nothing else is necessary:

import * as PlayHT from 'playht';

const stream = await PlayHT.stream('Now using new HFVC backend', {
  voiceEngine: 'PlayDialog',
  voiceId: '<your High-Fidelity Voice Clone voice id>',
});

0.19.0

This version introduces a new inference backend specialized in High-Fidelity Voice Clones of our PlayDialog model. If you already are using PlayDialog as model, nothing else is necessary:

import * as PlayHT from 'playht';

const stream = await PlayHT.stream('Now using new HFVC backend', {
  voiceEngine: 'PlayDialog',
  voiceId: '<your High-Fidelity Voice Clone voice id>',
});

0.18.0

Debug mode

Now settings allow debug mode which will log request ids and other information on each TTS request issued by the SDK:

PlayHT.init({
  userId: E2E_CONFIG.USER_ID,
  apiKey: E2E_CONFIG.API_KEY,
  debug: {
    enabled: true,
  },
});

Hindi model backend for PlayDialog

When users specify engine PlayDialog and language='hindi' their requests are now sent to the new, improved, Hindi TTS PlayDialog cluster and model.

Example:

const streamFromText = await PlayHT.stream('हैलो वर्ल्ड!', {
  voiceEngine: 'PlayDialog',
  language: 'hindi'
});

0.17.0

This version introduces the PlayDialog-turbo voice engine, a new high-performance voice engine that provides faster response times while maintaining same audio quality.

Example:

import * as PlayHT from 'playht';

const stream = await PlayHT.stream('Get real-time responses with PlayDialog-turbo.', {
  voiceEngine: 'PlayDialog-turbo',
  voiceId: 'Celeste-PlayAI',
  language: 'english',
});

0.16.0

When users specify engine PlayDialog and language='arabic' their requests are now sent to the new, improved, Arabic TTS PlayDialog cluster.

Example:

const streamFromText = await PlayHT.stream('مرحباً بالعالم', {
  voiceEngine: 'PlayDialog',
  language: 'arabic'
});

0.15.0

Adds two new output formats to the Play3.0-mini and PlayDialog engines: pcm and wav_mulaw.

To use them, provide the outputFormat param in the PlayHT.stream() method:

const streamFromText = await PlayHT.stream('Hello, world.', {
  voiceEngine: 'Play3.0-mini',
  outputFormat: 'pcm',
});

New values are:

• pcm: requests audio in the PCM format.
• wav_mulaw: generates audio with WAV header format with mulaw sample encoding. Note that the mulaw output format generates mulaw headerless.

0.14.0

Introducing PlayDialog – PlayHT's latest voice model built for fluid, emotive conversation. It's a more advanced model that can generate turn-based dialogues with multiple voices.

NEW TTS Model: PlayDialog. Try it out now.

---

Upgrading Play's SDK to use PlayDialog

• First upgrade the package (should upgrade to 0.14.0):

npm install playht@latest

• When calling PlayHT.stream(), the voiceEngine argument should be "PlayDialog".
• PlayDialog is multilingual! English is the default; to use a language other than English, pass a language as the language argument on the options of PlayHT.stream().

v0.12.0

Introducing Play 3.0 mini – A lightweight, reliable and cost-efficient Multilingual Text-to-Speech model

NEW TTS Model: Play3.0-mini. Faster, more expressive, reliable, and cost effective. Try it out now.

---

Upgrading Play's SDK to use Play3.0-mini

• First upgrade the package (should upgrade to 0.10.x):

npm install playht@latest

• When calling PlayHT.stream(), the voiceEngine argument should be "Play3.0-mini".
• Play3.0 is multilingual! English is the default; to use a language other than English, pass a language as the language argument on the options of PlayHT.stream().

0.10.0

Introducing Play 3.0 mini – A lightweight, reliable and cost-efficient Multilingual Text-to-Speech model

NEW TTS Model: Play3.0-mini. Faster, more expressive, reliable, and cost effective. Try it out now.

---

Upgrading Play's SDK to use Play3.0-mini

• First upgrade the package (should upgrade to 0.10.x):

npm install playht@latest

• When calling PlayHT.stream(), the voiceEngine argument should be "Play3.0-mini".
• Play3.0 is multilingual! English is the default; to use a language other than English, pass a language as the language argument on the options of PlayHT.stream().