The AI toolkit for speech

Create realistic, human-like speech and transcribe audio with a unified API that works with leading AI providers like OpenAI, ElevenLabs and AssemblyAI.

npm i orate

View on GitHub

Plug and play your favorite AI speech provider

Text to speech

Generate realistic speech with AI

Convert your text into lifelike speech using our simple API that integrates seamlessly with many leading AI providers.

import { speak } from 'orate';
import { elevenlabs } from 'orate/elevenlabs';

const speech = await speak({
  model: elevenlabs.tts('multilingual_v2', 'aria'),
  prompt: 'Friends, Romans, countrymen, lend me your ears!'
});

Read the docs

Speech to text

Transcribe complex audio into text

Transform spoken words into meaningful text with unparalleled accuracy, speed and reliability; powered by leading AI providers.

import { transcribe } from 'orate';
import { assembly } from 'orate/assembly';
import audio from './audio.wav';

const text = await transcribe({
  model: assembly.stt('best'),
  audio,
});

Read the docs

Speech to speech

Flow from one voice to another

Change the voice of your audio using our simple voice-to-voice API that works with leading AI providers.

import { speak } from 'orate';
import { elevenlabs } from 'orate/elevenlabs';
import audio from './audio.wav';

const speech = await change({
  model: elevenlabs.sts('multilingual_v2', 'aria'),
  audio,
});

Read the docs

Speech isolation

Find the signal in the noise

Transform audio recordings with background noise into clean, studio-quality speech. Powered by leading AI providers.

import { isolate } from 'orate';
import { elevenlabs } from 'orate/elevenlabs';
import audio from './audio.wav';

const speech = await isolate({
  model: elevenlabs.isl(),
  audio,
});

Read the docs

Install and use in seconds

Install Orate with your favorite package manager and start speaking and transcribing audio in seconds.

npm i orate