CleanVoice

Cleanvoice helps you remove background noise, filler words, long silence, and mouth sounds from your podcast using AI. Orate supports Cleanvoice's speech-to-text and speech isolation services.

Setup

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

import { cleanvoice } from 'orate/cleanvoice';

Configuration

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

CLEANVOICE_API_KEY="your_api_key"

Usage

The CleanVoice provider provides a single interface for all of CleanVoice's speech services.

Speech to Text

The CleanVoice provider provides a stt function that allows you to create a speech-to-text transcription function using CleanVoice.

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

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

const text = await transcribe({
  model: cleanvoice.stt({
    long_silences: true,
  }),
  audio: new File(...),
});

Speech Isolation

The CleanVoice provider provides a isl function that allows you to isolate the speech from the audio.

import { isolate } from 'orate';
import { cleanvoice } from 'orate/cleanvoice';
 
const speech = await isolate({
  model: cleanvoice.isl(),
  audio: new File(...),
});

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

const speech = await isolate({
  model: cleanvoice.isl({
    long_silences: true,
  }),
  audio: new File(...),
});