Skip to main content
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
Find all available voice models HERE.

​
Request

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

​
Example​

​
Body

json
{   
  "key": "enterprise_api_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
}

​
Body Attributes

​
key
string
required
Your API Key used for request authorization.
​
init_audio
string
required
URL (YouTube links supported) or valid .wav file base64 data whose audio you want to clone with the model.
​
model_id
string
required
ID of the voice cover model Find Models Here.
​
pitch
string
default:"none"
Voice pitch conversion. Options:
  • m2f: Male-to-Female
  • f2m: Female-to-Male
  • none: No pitch conversion
​
algorithm
string
default:"rmvpe"
Pitch detection algorithm. Default: rmvpe.
​
rate
number
default:"0.5"
Rate of control for generated voice leakage. Higher values bias model towards training data. Default: 0.5.
​
seed
integer
Seed for reproducibility. Same seed gives the same output. Pass null for a random seed.
​
language
string
default:"english"
The language of the cloned voice. Default: english.
​
emotion
string
default:"neutral"
Emotional tone of the generated voice. Default: neutral.
​
speed
number
default:"1.0"
Floating point value for playback speed of the speaker. Default: 1.0.
​
radius
integer
default:"3"
Median filtering length to reduce breathiness and artifacts. Default: 3.
​
mix
number
default:"0.25"
Mix between original loudness and fixed loudness. Default: 0.25.
​
hop_length
integer
Hop length for pitch changes (only applies when using mangio-crepe).
​
originality
number
default:"0.33"
Controls similarity to original vocals (voiceless consonants). Default: 0.33.
​
lead_voice_volume_delta
number
Adjust lead vocals volume. Range: -5 (decrease) to +5 (increase).
​
backup_voice_volume_delta
number
Adjust backup vocals volume. Range: -5 (decrease) to +5 (increase).
​
instrument_volume_delta
number
Adjust instrumental volume. Range: -5 (decrease) to +5 (increase).
​
reverb_size
number
default:"0.15"
Reverb room size. Default: 0.15.
​
wetness
number
default:"0.2"
Reverb for generated vocals. Default: 0.2.
​
dryness
number
default:"0.8"
Reverb for original vocals. Default: 0.8.
​
damping
number
default:"0.7"
High-frequency damping factor in reverb. Default: 0.7.
​
base64
boolean
default:"false"
Whether the input sound clip is in base64 format. Default: false.
​
temp
boolean
default:"false"
Whether you want the output to be auto-deleted from the server after a short time. Default: false.
​
webhook
string
A URL to receive a POST API call once the voice cloning process is complete.
​
track_id
string
This ID is returned in the webhook callback to identify the request.
⌘I