IBM Watson

IBM offers a portfolio of AI products that accelerate generative AI into core workflows, driving automation and productivity, including IBM Watson Speech to Text and Text to Speech.

Setup

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

import { IBM } from 'orate/ibm';

Configuration

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

const ibm = new IBM();

This will use the IBM_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 ibm = new IBM('your_api_key');

Usage

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

Text to Speech

The IBM provider provides a tts function that allows you to create a text-to-speech synthesis function using IBM Text to Speech. By default, the tts function uses the en-US_AllisonV3Voice voice.

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

You can specify the model and voice to use by passing them as arguments to the tts function.

const speech = await speak({
  model: new IBM().tts('en-AU_HeidiExpressive'),
  prompt: 'Hello, world!',
});

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

const speech = await speak({
  model: new IBM().tts('en-AU_HeidiExpressive', {
    pitchPercentage: 5,
  }),
  prompt: 'Hello, world!',
});

You can also stream the speech.

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

Speech to Text

The IBM provider provides a stt function that allows you to create a speech-to-text transcription function using IBM Speech to Text. By default, the stt function uses the en-US_BroadbandModel model.

import { transcribe } from 'orate';
import { IBM } from 'orate/ibm';
 
const text = await transcribe({
  model: new IBM().stt(),
  audio: new File(...),
});

You can specify the model to use by passing it as an argument to the stt function.

const text = await transcribe({
  model: new IBM().stt('ar-MS_Telephony'),
  audio: new File(...),
});

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

const text = await transcribe({
  model: new IBM().stt('ar-MS_Telephony', {
    smartFormatting: true,
  }),
  audio: new File(...),
});