Main sonic traits
Selected-sample labels, grouped by what they describe.
This voice model is based on Michael Jackson during the 1991 Dangerous era, capturing his expressive tone, signature falsettos, and iconic vocal ad-libs (“Hee-hee!”, “Shamone!”). It aims to reproduce the powerful, emotional sound heard during the Dangerous album and world tour.
🎼 Dataset
Total Duration: 30 minutes
Content Included:
Studio acapellas (isolated vocals)
Multitrack stems and vocal layers
Official album songs from Dangerous
Unreleased demos and rehearsal clips
All audio was cleaned and curated to preserve clarity, dynamics, and characteristic MJ expressions.
⚙️ Training Details
Model Type: RVC V2
Pitch & Expression: RVMPE enhancement
Vocoder: KLM HiFiGAN (high fidelity)
Epochs: 500 (for stability and realism) https://huggingface.co/JEFFERSONMUSIC/MjDangerousEra40KV1/resolve/main/MjDangerousEra40K.zip?download=true
Tags: No tags available
Download Link: https://huggingface.co/JEFFERSONMUSIC/MjDangerousEra40KV1/resolve/main/MjDangerousEra40K.zip?download=true Hosted on Hugging Face
Convert this model in EasyAIVoice
Selected-sample labels, grouped by what they describe.
Pick a pitch, compare the Quality Score, then Run. Hold Ctrl or Cmd to select multiple pitches.
Nearby voices from generated samples. Pick a pitch in the Sample Deck to refresh the matches.