Enterprise: Voice Cover Endpoint

Overview

Voice cover endpoint allows you to create an audio from an existing audio with a model. Get all voice models HERE .

caution

Make sure you add your s3 details for voice_cloning server, so you can receive image generated in your bucket. Images generated without s3 details being added will be delete after 24 hours

Request

--request POST 'https://modelslab.com/api/v1/enterprise/voice/voice_cover' \

Make a POST request to https://modelslab.com/api/v1/enterprise/voice/voice_cover endpoint and pass the required parameters as a request body.

Body Attributes

Parameter	Description
key	Your API Key used for request authorization
init_audio	URL (Youtube links supported) or valid .wav file base64 data whose audio you want to clone with the model.
model_id	ID of the voice cloning model get model_id from here.
pitch	One of ["m2f", "f2m", "none"]. If input voice is a male voice and model used is a trained female voice model, specify "m2f". Similar for the case of female-to-male. In other cases, specify "none".
algorithm	One of rmvpe, mangio-crepe. Defaults to rmvpe
rate	Rate of control for generated voice leakage. Higher values bias model towards training data. Defaults to 0.5. Should be between 0 and 1.
seed	Seed is used to reproduce results, same seed will give you same image in return again. Pass null for a random number.
language	The language of the voice. The supported languages includes english, arabic, brazilian, portuguese,chinese, dutch, english, french, hindi, hungarian, italian, japanese, korean, polish, russian, turkish. Default is english
emotion	One of neutral, happy, sad, angry,dull. Defaults to neutral
speed	Floating point value for speed of speaker. Defaults to 1.0
radius	Median filtering length to reduce breathiness and other minor voice artifacts. Defaults to 3.
mix	A value between 0 and 1. A lower value leads to similar loudness to the original sound clip while a higher value leans towards fixed loudness. Defaults to 0.25.
hop_length	How often to check for pitch changes when using mangio-crepe as algorithm.
originality	Control how much similarity to maintain with the original vocals voiceless constants. Defaults to 0.33.
lead_voice_volume_delta	A value between -5 and +5 controlling whether lead vocals should be decreased or increased.
backup_voice_volume_delta	A value between -5 and +5 controlling whether backup vocals should be decreased or increased
instrument_volume_delta	A value between -5 and +5 controlling whether instrumental volume should be decreased or increased.
reverb_size	Reverb room size. Defaults to 0.15. Should be between 0 and 1.
wetness	Reverb for generated vocals. Defaults to 0.2. Should be between 0 and 1.
dryness	Reverb for original vocals. Defaults to 0.8. Should be between 0 and 1.
damping	Damping factor for high frequencies in the reverb. Defaults to 0.7. Should be between 0 and 1.
base64	Whether the input sound clip is in base64 or not. Should be true or false. Defaults to false.
temp	Whether you want the output to be auto-deleted from our server in a short amount of time.
webhook	Set an URL to get a POST API call once the image generation is complete.
track_id	This ID is returned in the response to the webhook API call. This will be used to identify the webhook request.

Example

Body

Body

{   
"key": "",
"init_audio": "https://music.youtube.com/watch?v=aZ1hziFhj1o",
"model_id": "zoro",
"pitch": "none",
"rate": 0.5,
"radius": 3,
"mix": 0.25,
"algorithm": "rmvpe",
"hop_length": 128,
"originality": 0.5,
"lead_voice_volume_delta": "+1",
"backup_voice_volume_delta": "-2",
"instrument_volume_delta":"+2",
"reverb_size": 0.15,
"wetness": 0.2,
"dryness": 0.8,
"damping": 0.7,
"base64": false,
"temp": false,
"webhook": null,
"track_id" : null
}

Request

JS

var myHeaders = new Headers();
myHeaders.append("Content-Type", "application/json");

var raw = JSON.stringify({
"key": "",
"init_audio": "https://music.youtube.com/watch?v=aZ1hziFhj1o",
"model_id": "zoro",
"pitch": "none",
"rate": 0.5,
"radius": 3,
"mix": 0.25,
"algorithm": "rmvpe",
"hop_length": 128,
"originality": 0.5,
"lead_voice_volume_delta": "+1",
"backup_voice_volume_delta": "-2",
"instrument_volume_delta":"+2",
"reverb_size": 0.15,
"wetness": 0.2,
"dryness": 0.8,
"damping": 0.7,
"base64": false,
"temp": false,
"webhook": null,
"track_id" : null
});

var requestOptions = {
  method: 'POST',
  headers: myHeaders,
  body: raw,
  redirect: 'follow'
};

fetch("https://modelslab.com/api/v1/enterprise/voice/voice_cover", requestOptions)
  .then(response => response.text())
  .then(result => console.log(result))
  .catch(error => console.log('error', error));

PHP

<?php

$payload = [
"key" => "",
"init_audio" => "https://music.youtube.com/watch?v=aZ1hziFhj1o",
"model_id" => "zoro",
"pitch" => "none",
"rate" => 0.5,
"radius" => 3,
"mix" => 0.25,
"algorithm" => "rmvpe",
"hop_length" => 128,
"originality" => 0.5,
"lead_voice_volume_delta" => "+1",
"backup_voice_volume_delta" => "-2",
"instrument_volume_delta":"+2",
"reverb_size" =>  0.15,
"wetness" => 0.2,
"dryness" => 0.8,
"damping" => 0.7,
"base64" => false,
"temp" => false,
"webhook" => null,
"track_id"  => null
];

$curl = curl_init();

curl_setopt_array($curl, array(
  CURLOPT_URL => 'https://modelslab.com/api/v1/enterprise/voice/voice_cover',
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => '',
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 0,
  CURLOPT_FOLLOWLOCATION => true,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => 'POST',
  CURLOPT_POSTFIELDS => json_encode($payload),
  CURLOPT_HTTPHEADER => array(
    'Content-Type: application/json'
  ),
));

$response = curl_exec($curl);

curl_close($curl);
echo $response;

NODE

var request = require('request');
var options = {
  'method': 'POST',
  'url': 'https://modelslab.com/api/v1/enterprise/voice/voice_cover',
  'headers': {
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
   "key": "",
"init_audio": "https://music.youtube.com/watch?v=aZ1hziFhj1o",
"model_id": "zoro",
"pitch": "none",
"rate": 0.5,
"radius": 3,
"mix": 0.25,
"algorithm": "rmvpe",
"hop_length": 128,
"originality": 0.5,
"lead_voice_volume_delta": "+1",
"backup_voice_volume_delta": "-2",
"instrument_volume_delta":"+2",
"reverb_size": 0.15,
"wetness": 0.2,
"dryness": 0.8,
"damping": 0.7,
"base64": false,
"temp": false,
"webhook": null,
"track_id" : null
  })
};

request(options, function (error, response) {
  if (error) throw new Error(error);
  console.log(response.body);
});

PYTHON

import requests
import json

url = "https://modelslab.com/api/v1/enterprise/voice/voice_cover"

payload = json.dumps({
 "key": "",
"init_audio": "https://music.youtube.com/watch?v=aZ1hziFhj1o",
"model_id": "zoro",
"pitch": "none",
"rate": 0.5,
"radius": 3,
"mix": 0.25,
"algorithm": "rmvpe",
"hop_length": 128,
"originality": 0.5,
"lead_voice_volume_delta": "+1",
"backup_voice_volume_delta": "-2",
"instrument_volume_delta":"+2",
"reverb_size": 0.15,
"wetness": 0.2,
"dryness": 0.8,
"damping": 0.7,
"base64": False,
"temp": False,
"webhook": None,
"track_id" : None
})

headers = {
  'Content-Type': 'application/json'
}

response = requests.request("POST", url, headers=headers, data=payload)

print(response.text)

JAVA

OkHttpClient client = new OkHttpClient().newBuilder()
  .build();
MediaType mediaType = MediaType.parse("application/json");
RequestBody body = RequestBody.create(mediaType, "{\n        \"key\":\"\",\n        \"init_audio\": \"https://music.youtube.com/watch?v=aZ1hziFhj1o\",\n        \"model_id\": \"zoro\",\n        \"pitch\": \"none\",\n        \"rate\": 0.5,\n        \"radius\": 3,\n        \"mix\": 0.25,\n        \"algorithm\": \"rmvpe\",\n        \"hop_length\": 128,\n        \"originality\": 0.5,\n        \"lead_voice_volume_delta\": \"+1\",\n        \"backup_voice_volume_delta\": \"-2\",\n        \"instrument_volume_delta\":\"+2\",\n        \"reverb_size\": 0.15,\n        \"wetness\": 0.2,\n        \"dryness\": 0.8,\n        \"damping\": 0.7,\n        \"base64\": false,\n        \"temp\": false\n}");
Request request = new Request.Builder()
  .url("https://modelslab.com/api/v1/enterprise/voice/voice_cover")
  .method("POST", body)
  .addHeader("Content-Type", "application/json")
  .build();
Response response = client.newCall(request).execute();

Response

{
    "generationTime": 1.5732920169830322,
    "id": 10,
    "links":  [
        "https://cdn2.stablediffusionapi.com/generations/bc1e5025-b140-4af6-be24-183fa18c943a.wav"
    ],
    "proxy_links": [
        "https://cdn2.stablediffusionapi.com/generations/bc1e5025-b140-4af6-be24-183fa18c943a.wav"
    ],
    "meta": {
        "algorithm": "rmvpe",
        "backup_voice_volume_delta": -2,
        "base64": "no",
        "damping": 0.7,
        "dryness": 0.8,
        "filename": "bc1e5025-b140-4af6-be24-183fa18c943a.wav",
        "hop_length": 128,
        "input_sound_clip": "https://music.youtube.com/watch?v=aZ1hziFhj1o",
        "instrument_volume_delta": 2,
        "is_youtube": true,
        "lead_voice_volume_delta": 1,
        "mix": 0.25,
        "model_id": "zoro",
        "originality": 0.5,
        "pitch": "none",
        "radius": 3,
        "rate": 0.5,
        "reverb_size": 0.15,
        "seed": 1216247535,
        "temp": "no",
        "wetness": 0.2
    },
    "status": "success",
}