Gladia

Gladia provide infrastructure to transform note-taking, customer support, sales assistance, user experience, and more. From async to live streaming, their API empowers your platform with accurate, multilingual speech-to-text and actionable insights.

Setup

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

import { gladia } from 'orate/gladia';

Configuration

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

GLADIA_API_KEY="your_api_key"

Usage

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

Speech to Text

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

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

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

const text = await transcribe({
  model: gladia.stt('enhanced', {
    chapterization: true,
  }),
  audio: someArrayBuffer,
});