AI Audio

AI Cover

Song cover — re-sing a track in a target voice (voice timbre transfer)

AI Cover is voice timbre transfer: convert a song (source_audio_url) into a target voice (reference_audio_url), with optional vocal/accompaniment separation and gain. Same contract as /api/v2/voice/convert — this is a song-cover-flavored alias. Async task; poll for status after submitting.

Base URL: https://api.aiclonevoicefree.com | Auth: Authorization: Bearer sk_...

POST /api/v2/voice/cover

FieldTypeRequiredNotes
source_audio_urlstringOriginal song audio URL
reference_audio_urlstringTarget voice reference audio URL
pitch_shiftintPitch shift in semitones, default 0
return_formatstringwav / mp3 / flac, default wav
enable_separationboolSeparate vocals/accompaniment first, default true
vocals_gainnumberVocal gain, default 1.0
accompaniment_gainnumberAccompaniment gain, default 0.8
diffusion_stepsintDiffusion steps, default 50
length_adjustnumberTime stretch, default 1.0
inference_cfg_ratenumberInference guidance [0-1], default 0.7
auto_f0_adjustboolAuto F0 adjustment, default true

Billing

2 credits/second of output (same as voice convert). 402 at submit if insufficient; auto-refunded on failure.

Example

curl -X POST https://api.aiclonevoicefree.com/api/v2/voice/cover \
  -H "Authorization: Bearer sk_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "source_audio_url": "https://your-cdn.com/song.mp3",
    "reference_audio_url": "https://your-cdn.com/target-voice.wav",
    "enable_separation": true,
    "pitch_shift": 0
  }'

Response 202{ "task_id": "...", "status": "pending", "capability": "voice", "action": "vocal-conversion" }

Getting the result

Poll GET /api/v2/tasks/{task_id}; audioUrl holds the result when done. See Tasks.

On this page