Model Information

Display Name: Zsxkib Voice Cover

API Model ID: zsxkib/voice

Category: Voice Cover

Description: Generate AI voice covers of any song using a trained voice model. Automatically separates vocals from instrumentals, applies your trained voice, and remixes everything together. ## How It Works 1. Train your voice first using zsxkib/train (one-time) 2. Send any song + your voice_id 3. Get back the song with your voice singing ## Parameters | Parameter | Type | Required | Default | Description | |-----------|------|----------|---------|-------------| | song | URL | Yes | — | Song audio file to cover (MP3, WAV) | | voice_id | string | Yes | — | Voice ID from zsxkib/train | | pitch_change | string | No | no-change | Pitch: no-change, male-to-female, female-to-male | | index_rate | number | No | 0.5 | AI accent retention (0-1) | | filter_radius | number | No | 3 | Audio smoothing (0-7) | | rms_mix_rate | number | No | 0.25 | Original loudness mix (0-1) | | protect | number | No | 0.33 | Preserve breath sounds (0-0.5) | | main_vocals_volume_change | number | No | 0 | AI vocals volume (dB) | | backup_vocals_volume_change | number | No | 0 | Backup vocals volume (dB) | | instrumental_volume_change | number | No | 0 | Instrumentals volume (dB) | | reverb_size | number | No | 0.15 | Reverb room size (0-1) | | reverb_wetness | number | No | 0.2 | Wet reverb level (0-1) | | reverb_dryness | number | No | 0.8 | Dry signal level (0-1) | | output_format | string | No | mp3 | Output format: mp3 or wav | ## Output Returns the song audio file with your voice singing.

How to Use This Model

To use Zsxkib Voice Cover via the HInow.ai API, use the model ID: zsxkib/voice

API Request Example

POST https://api.hinow.ai/v1/chat/completions
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

{
  "model": "zsxkib/voice",
  "messages": [
    {"role": "user", "content": "Your input here"}
  ]
}
              

Pricing

• total: $0.10

Available Parameters

• song: Song audio file URL to cover (MP3, WAV)
• voice_id: Voice ID from zsxkib/train
• pitch_change: Pitch shift for AI vocals. Default: no-change (Options: no-change, male-to-female, female-to-male)
• index_rate: AI accent retention 0-1 (0=less, 1=more). Default: 0.5
• filter_radius: Audio smoothing 0-7. Default: 3
• rms_mix_rate: Original loudness mix 0-1. Default: 0.25
• pitch_detection_algorithm: Pitch extraction method. Default: rmvpe (Options: rmvpe, mangio-crepe)
• protect: Preserve breath sounds 0-0.5. Default: 0.33
• main_vocals_volume_change: AI vocals volume in dB. Default: 0
• backup_vocals_volume_change: Backup vocals volume in dB. Default: 0
• instrumental_volume_change: Instrumentals volume in dB. Default: 0
• pitch_change_all: Pitch/key change for all audio in semitones. Default: 0
• reverb_size: Reverb room size 0-1. Default: 0.15
• reverb_wetness: Wet reverb level 0-1. Default: 0.2
• reverb_dryness: Dry signal level 0-1. Default: 0.8
• reverb_damping: High-frequency reverb absorption 0-1. Default: 0.7
• output_format: Output audio format. Default: mp3 (Options: mp3, wav)

Quick Reference

To use this model, set: "model": "zsxkib/voice"

Featured: No

Documentation: https://hinow.ai/models/zsxkib/voice

API Endpoint: https://api.hinow.ai/v1