Speech to Speech

Orate provides a simple and unified API for changing the voice of your audio using various AI providers. The speech-to-speech functionality is accessible through the change function.

Usage

The basic usage involves importing the change function from Orate and your chosen provider. For example, to use ElevenLabs' speech-to-speech model, you can import the ElevenLabs provider and use its sts function:

import { change } from 'orate';
import { elevenlabs } from 'orate/elevenlabs';
import audioFile from './audio.wav';
 
const newAudio = await change({
  model: elevenlabs.sts(),
  audio: audioFile,
});

model

The model parameter is a function that returns a model instance. The model instance is a function that takes an audio file and returns a promise that resolves to the new audio.

const model = elevenlabs.sts();

audio

The audio parameter is a File object that contains the audio data to be changed.

const audio = new File([audioBuffer], 'audio.wav', { type: 'audio/wav' });

Orate uses a File object because it is supported by all major browsers and can be easily converted to other formats. Additionally, the various AI providers require the audio data to be in a specific format, and the File object is the most convenient way to determine the audio format.