Song Cover

Transform voice in audio using AI models

curl --request POST \
  --url https://modelslab.com/api/v6/voice/voice_cover \
  --header 'Content-Type: application/json' \
  --data '{
  "key": "<string>",
  "init_audio": "<string>",
  "model_id": "<string>",
  "pitch": "m2f",
  "algorithm": "rmvpe",
  "rate": 0.5,
  "seed": 123,
  "language": "english",
  "emotion": "neutral",
  "speed": 1,
  "radius": 3,
  "mix": 0.25,
  "hop_length": 123,
  "originality": 0.33,
  "lead_voice_volume_delta": "<string>",
  "backup_voice_volume_delta": "<string>",
  "instrument_volume_delta": "<string>",
  "reverb_size": 0.15,
  "wetness": 0.2,
  "dryness": 0.8,
  "damping": 0.7,
  "base64": false,
  "temp": false,
  "webhook": "<string>",
  "track_id": 123
}'

{
  "status": "success",
  "generationTime": 123,
  "id": 123,
  "output": [
    "<string>"
  ],
  "proxy_links": [
    "<string>"
  ],
  "future_links": [
    "<string>"
  ],
  "links": [
    "<string>"
  ],
  "meta": {},
  "eta": 123,
  "message": "<string>",
  "tip": "<string>",
  "fetch_result": "<string>",
  "audio_time": 123
}

POST

voice

voice_cover

Transform voice in audio using AI models

curl --request POST \
  --url https://modelslab.com/api/v6/voice/voice_cover \
  --header 'Content-Type: application/json' \
  --data '{
  "key": "<string>",
  "init_audio": "<string>",
  "model_id": "<string>",
  "pitch": "m2f",
  "algorithm": "rmvpe",
  "rate": 0.5,
  "seed": 123,
  "language": "english",
  "emotion": "neutral",
  "speed": 1,
  "radius": 3,
  "mix": 0.25,
  "hop_length": 123,
  "originality": 0.33,
  "lead_voice_volume_delta": "<string>",
  "backup_voice_volume_delta": "<string>",
  "instrument_volume_delta": "<string>",
  "reverb_size": 0.15,
  "wetness": 0.2,
  "dryness": 0.8,
  "damping": 0.7,
  "base64": false,
  "temp": false,
  "webhook": "<string>",
  "track_id": 123
}'

{
  "status": "success",
  "generationTime": 123,
  "id": 123,
  "output": [
    "<string>"
  ],
  "proxy_links": [
    "<string>"
  ],
  "future_links": [
    "<string>"
  ],
  "links": [
    "<string>"
  ],
  "meta": {},
  "eta": 123,
  "message": "<string>",
  "tip": "<string>",
  "fetch_result": "<string>",
  "audio_time": 123
}

Request

Make a POST request to below endpoint and pass the required parameters as a request body.

curl

--request POST 'https://modelslab.com/api/v6/voice/voice_cover' \

Body

json

{
    "key": "your_api_key",
    "init_audio": "https://www.youtube.com/watch?v=ixkoVwKQaJg",
    "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
}

Body

application/json

key

string

required

API key to authorize the request

init_audio

string

required

URL (YouTube supported) or base64 WAV file for audio to be cloned

model_id

string

required

ID of the voice cloning model Find Models Here

pitch

enum<string>

Controls pitch transformation between voices

Available options:

m2f,

f2m,

none

algorithm

enum<string>

default:rmvpe

Algorithm used for voice cloning

Available options:

rmvpe,

mangio-crepe

rate

number

Controls generated voice resemblance to training data

Required range: 0 <= x <= 1

seed

integer

Seed value to reproduce results (null for random)

language

string

default:english

Language for the voice

emotion

enum<string>

default:neutral

Emotion of the voice

Available options:

neutral,

happy,

sad,

angry,

dull

speed

number

default:1

Playback speed of the speaker

Required range: 0.5 <= x <= 2

radius

number

default:3

Median filtering length to reduce voice artifacts

Required range: 0 <= x <= 3

mix

number

default:0.25

Controls loudness similarity to original audio

Required range: 0 <= x <= 1

hop_length

integer

Frequency of pitch analysis (mangio-crepe algorithm)

originality

number

default:0.33

Controls similarity to original vocals' voiceless consonants

Required range: 0 <= x <= 1

lead_voice_volume_delta

string

Adjusts volume of lead vocals (-5 to +5)

backup_voice_volume_delta

string

Adjusts volume of backup vocals (-5 to +5)

instrument_volume_delta

string

Adjusts volume of instrumental tracks (-5 to +5)

reverb_size

number

default:0.15

Size of the reverb room

Required range: 0 <= x <= 1

wetness

number

default:0.2

Reverb applied to generated vocals

Required range: 0 <= x <= 1

dryness

number

default:0.8

Reverb applied to original vocals

Required range: 0 <= x <= 1

damping

number

default:0.7

Damping factor for high frequencies in reverb

Required range: 0 <= x <= 1

base64

boolean

default:false

Whether input sound clip is in base64 format

temp

boolean

default:false

Use temporary links valid for 24 hours

webhook

string<uri>

URL to receive POST notification upon completion

track_id

integer

ID for webhook identification

Response

Voice cover response

status

enum<string>

Status of the voice generation

Available options:

success,

processing,

error

generationTime

number

Time taken to generate the audio in seconds

integer

Unique identifier for the voice generation

output

string<uri>[]

Array of generated audio URLs

proxy_links

string<uri>[]

Array of proxy audio URLs

future_links

string<uri>[]

Array of future audio URLs for queued requests

links

string<uri>[]

Array of audio URLs (voice cover response)

Using the APIs

Our AI APIs

Request

Body

Body

Response

Using the APIs

Our AI APIs

​Request

​Body

Body

Response

Request

Body