Neuphonic

Neuphonic provides hyper-realistic and realtime voice experiences. It enables seamless speech generation, powers voice applications, and offers voice cloning capabilities on an ultra-fast AI platform.

Setup

The Neuphonic provider is available by default in Orate. To import it, you can use the following code:

import { Neuphonic } from 'orate/neuphonic';

Configuration

You can use Neuphonic by creating a new instance of the Neuphonic class:

const neuphonic = new Neuphonic();

This will use the NEUPHONIC_API_KEY environment variable. If you don't have this variable set, you can pass your API key as an argument to the constructor.

const neuphonic = new Neuphonic('your_api_key');

Usage

The Neuphonic provider provides a single interface for all of Neuphonic's speech and transcription services.

Text to Speech

The Neuphonic provider provides a tts function that allows you to create a text-to-speech synthesis function using Neuphonic.

import { speak } from 'orate';
import { Neuphonic } from 'orate/neuphonic';
 
const speech = await speak({
  model: new Neuphonic().tts(),
  prompt: 'Hello, world!',
});

You can specify the voice to use by passing it as an argument to the tts function.

const speech = await speak({
  model: new Neuphonic().tts('Emily'),
  prompt: 'Hello, world!',
});

The voice can be the name of a default voice e.g. Emily or the ID of a custom cloned voice.

You can also specify specific Neuphonic properties by passing them as an argument to the tts function.

const speech = await speak({
  model: new Neuphonic().tts('Emily', {
    speed: 1.5
  }),
  prompt: 'Hello, world!',
});