Rev AI

Rev AI offers an accurate API for AI and human-generated transcripts. Trained from the most diverse collection of voices in the world, Rev AI sets the accuracy standard for video and voice applications.

Setup

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

import { rev } from 'orate/rev';

Configuration

The Rev AI provider looks for the REV_API_KEY environment variable. This variable is required for the provider to work. Simply add the following to your .env file:

REV_API_KEY="your_api_key"

Usage

The Rev AI provider provides a single interface for all of Rev AI's transcription services.

Speech to Text

The Rev AI provider provides a stt function that allows you to create a speech-to-text transcription function using Rev AI. By default, the stt function uses the machine model.

import { transcribe } from 'orate';
import { rev } from 'orate/rev';
 
const text = await transcribe({
  model: rev.stt(),
  audio: someArrayBuffer,
});

You can specify the model to use by passing it as an argument to the stt function. By default, the stt function uses the base model.

const text = await transcribe({
  model: rev.stt('fusion'),
  audio: someArrayBuffer,
});

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

const text = await transcribe({
  model: rev.stt('fusion', {
    remove_disfluencies: true,
  }),
  audio: someArrayBuffer,
});