zsxkib/realistic-voice-cloning 🔢❓🖼️📝 → 🖼️
About
Create song covers with any RVC v2 trained AI voice from audio files.
Example Output
Output
Performance Metrics
2.81s
Prediction Time
2.83s
Total Time
All Input Parameters
{
"protect": 0.33,
"rvc_model": "Squidward",
"index_rate": 0.5,
"song_input": "https://replicate.delivery/pbxt/JsPIizFfRy54Jk5LuXdnrNdV1JHJ6oLmPPdRuIfh3lvpoNai/gangnam.mp3",
"reverb_size": 0.15,
"pitch_change": "no-change",
"rms_mix_rate": 0.25,
"filter_radius": 3,
"output_format": "mp3",
"reverb_damping": 0.7,
"reverb_dryness": 0.8,
"reverb_wetness": 0.2,
"crepe_hop_length": 128,
"pitch_change_all": 0,
"main_vocals_volume_change": 10,
"pitch_detection_algorithm": "rmvpe",
"instrumental_volume_change": 0,
"backup_vocals_volume_change": 0
}
Input Parameters
- protect
- Control how much of the original vocals' breath and voiceless consonants to leave in the AI vocals. Set 0.5 to disable.
- rvc_model
- RVC model for a specific voice. If using a custom model, this should match the name of the downloaded model. If a 'custom_rvc_model_download_url' is provided, this will be automatically set to the name of the downloaded model.
- index_rate
- Control how much of the AI's accent to leave in the vocals.
- song_input
- Upload your audio file here.
- reverb_size
- The larger the room, the longer the reverb time.
- pitch_change
- Adjust pitch of AI vocals. Options: `no-change`, `male-to-female`, `female-to-male`.
- rms_mix_rate
- Control how much to use the original vocal's loudness (0) or a fixed loudness (1).
- filter_radius
- If >=3: apply median filtering median filtering to the harvested pitch results.
- output_format
- wav for best quality and large file size, mp3 for decent quality and small file size.
- reverb_damping
- Absorption of high frequencies in the reverb.
- reverb_dryness
- Level of AI vocals without reverb.
- reverb_wetness
- Level of AI vocals with reverb.
- crepe_hop_length
- When `pitch_detection_algo` is set to `mangio-crepe`, this controls how often it checks for pitch changes in milliseconds. Lower values lead to longer conversions and higher risk of voice cracks, but better pitch accuracy.
- pitch_change_all
- Change pitch/key of background music, backup vocals and AI vocals in semitones. Reduces sound quality slightly.
- main_vocals_volume_change
- Control volume of main AI vocals. Use -3 to decrease the volume by 3 decibels, or 3 to increase the volume by 3 decibels.
- pitch_detection_algorithm
- Best option is rmvpe (clarity in vocals), then mangio-crepe (smoother vocals).
- instrumental_volume_change
- Control volume of the background music/instrumentals.
- backup_vocals_volume_change
- Control volume of backup AI vocals.
- custom_rvc_model_download_url
- URL to download a custom RVC model. If provided, the model will be downloaded (if it doesn't already exist) and used for prediction, regardless of the 'rvc_model' value.
Output Schema
Output
Example Execution Logs
[~] Starting AI Cover Generation Pipeline... [~] Applying audio effects to Vocals... [~] Combining AI Vocals and Instrumentals... [~] Removing intermediate audio files... [+] Cover generated at /src/song_output/d0386572142/tmp11cudxj_gangnam (Squidward Ver).mp3
Version Details
- Version ID
0a9c7c558af4c0f20667c1bd1260ce32a2879944a0b9e44e1398660c077b1550- Version Created
- November 15, 2023