🎉 New Year Sale: Get 20% OFF on all plans — Use code NEWYEAR2026.

Upgrade now
Voice Cover thumbnail

ModelsLab/Voice Cover

voice-cover
The Voice Cover endpoint allows you to transform a song or audio file into a celeb/fictional character/singer/politician voice using a proper model id of that character.
API PlaygroundAPI Documentation

API Endpoint URL

Base URL for all API requests to this endpoint.

https://modelslab.com/api/v6/voice/voice_cover

API Authentication

Authentication requires a valid API key included in the request. Generate and manage your API keys from your developer dashboard. Include the key in the key parameter for all API requests.

Integration Examples

Production-ready code samples for API integration

{
"init_audio": "https://www.youtube.com/watch?v=ixkoVwKQaJg",
"model_id": "voice-cover",
"language": "english",
"pitch": "none",
"base64": "false",
"algorithm": "rmvpe",
"rate": "0.5",
"emotion": "neutral",
"radius": "3",
"speed": "1",
"mix": "0.25",
"originality": "0.33",
"lead_voice_volume_delta": "+1",
"backup_voice_volume_delta": "-2",
"instrument_volume_delta": "+2",
" reverb_size": "0.15",
"wetness": "0.2",
"damping": "0.7",
"webhook": null,
" track_id": null,
"key": "YOUR_API_KEY"
}

SDKs

Official SDKs

Production-ready SDKs and client libraries for all major programming languages

API Parameters

Technical specifications for API request parameters.

Field NameParameterTechnical Description
Init Audioinit_audioInit Audio
Model IDmodel_idModel ID
languagelanguageThe language for the voice. arabic, brazilian portuguese, chinese, dutch, french, hindi, hungarian, italian, japanese, korean, polish, russian, turkish. Default is english.
pitchpitchUse none when the provided audio singer is male and model id is male. use m2f when the provided audio is male anf the model id is female. use f2m when the provided audio is female anf the model id is male
base64base64Indicates if the input sound clip is in base64 format. Defaults to false.
algorithmalgorithmAlgorithm used for voice cloning
raterateControls generated voice resemblance to training data
emotionemotionEmotion of the voice
radiusradiusMedian filtering length to reduce voice artifacts
speedspeedPlayback speed of the speaker
mixmixControls loudness similarity to original audio
originalityoriginalityControls similarity to original vocals' voiceless consonants
lead_voice_volume_deltalead_voice_volume_deltaAdjusts volume of lead vocals (-5 to +5)
backup_voice_volume_deltabackup_voice_volume_deltaAdjusts volume of backup vocals (-5 to +5)
instrument_volume_deltainstrument_volume_deltaAdjusts volume of instrumental tracks (-5 to +5)
reverb_size reverb_sizeSize of the reverb room
wetnesswetnessReverb applied to original vocals
dampingdampingDamping factor for high frequencies in reverb
webhookwebhookURL to receive POST notification upon completion
track_id track_idID for webhook identification