Prediction
zsxkib/realistic-voice-cloning:0a9c7c558af4c0f20667c1bd1260ce32a2879944a0b9e44e1398660c077b1550Input
- protect
- 0.33
- rvc_model
- CUSTOM
- index_rate
- 0.5
- song_input
- Video Player is loading.Current Time 00:00:000/Duration 00:00:000Loaded: 0%00:00:000Stream Type LIVERemaining Time -00:00:0001x
- Chapters
- descriptions off, selected
- captions settings, opens captions settings dialog
- captions off, selected
This is a modal window.
Beginning of dialog window. Escape will cancel and close the window.
End of dialog window.
- 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
- custom_rvc_model_download_url
- https://huggingface.co/CxronaBxndit/Morgan-Freeman/resolve/main/Morgan-Freeman.zip
{
"protect": 0.33,
"rvc_model": "CUSTOM",
"index_rate": 0.5,
"song_input": "https://replicate.delivery/pbxt/JyMOAadCqhOZxgTZ8ZQUTCERdoh26oGM2nIJP67lSLWGZQnd/silence-lambs-trimmed.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,
"custom_rvc_model_download_url": "https://huggingface.co/CxronaBxndit/Morgan-Freeman/resolve/main/Morgan-Freeman.zip"
}Install Replicate’s Node.js client library:
npm install replicateSet the
REPLICATE_API_TOKEN environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import and set up the client:
import Replicate from "replicate";
const replicate = new Replicate({
auth: process.env.REPLICATE_API_TOKEN,
});Run zsxkib/realistic-voice-cloning using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"zsxkib/realistic-voice-cloning:0a9c7c558af4c0f20667c1bd1260ce32a2879944a0b9e44e1398660c077b1550",
{
input: {
protect: 0.33,
rvc_model: "CUSTOM",
index_rate: 0.5,
song_input: "https://replicate.delivery/pbxt/JyMOAadCqhOZxgTZ8ZQUTCERdoh26oGM2nIJP67lSLWGZQnd/silence-lambs-trimmed.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,
custom_rvc_model_download_url: "https://huggingface.co/CxronaBxndit/Morgan-Freeman/resolve/main/Morgan-Freeman.zip"
}
}
);
// To access the file URL:
console.log(output.url()); //=> "http://example.com"
// To write the file to disk:
fs.writeFile("my-image.png", output);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:
pip install replicateSet the
REPLICATE_API_TOKEN environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import the client:
import replicateRun zsxkib/realistic-voice-cloning using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"zsxkib/realistic-voice-cloning:0a9c7c558af4c0f20667c1bd1260ce32a2879944a0b9e44e1398660c077b1550",
input={
"protect": 0.33,
"rvc_model": "CUSTOM",
"index_rate": 0.5,
"song_input": "https://replicate.delivery/pbxt/JyMOAadCqhOZxgTZ8ZQUTCERdoh26oGM2nIJP67lSLWGZQnd/silence-lambs-trimmed.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,
"custom_rvc_model_download_url": "https://huggingface.co/CxronaBxndit/Morgan-Freeman/resolve/main/Morgan-Freeman.zip"
}
)
print(output)To learn more, take a look at the guide on getting started with Python.
Set the
REPLICATE_API_TOKEN environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run zsxkib/realistic-voice-cloning using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \
-H "Authorization: Bearer $REPLICATE_API_TOKEN" \
-H "Content-Type: application/json" \
-H "Prefer: wait" \
-d $'{
"version": "0a9c7c558af4c0f20667c1bd1260ce32a2879944a0b9e44e1398660c077b1550",
"input": {
"protect": 0.33,
"rvc_model": "CUSTOM",
"index_rate": 0.5,
"song_input": "https://replicate.delivery/pbxt/JyMOAadCqhOZxgTZ8ZQUTCERdoh26oGM2nIJP67lSLWGZQnd/silence-lambs-trimmed.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,
"custom_rvc_model_download_url": "https://huggingface.co/CxronaBxndit/Morgan-Freeman/resolve/main/Morgan-Freeman.zip"
}
}' \
https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
Video Player is loading.
Current Time 00:00:000
/
Duration 00:00:000
Loaded: 0%
00:00:000
Stream Type LIVE
Remaining Time -00:00:000
1x
- Chapters
- descriptions off, selected
- captions settings, opens captions settings dialog
- captions off, selected
This is a modal window.
Beginning of dialog window. Escape will cancel and close the window.
End of dialog window.
{
"completed_at": "2023-12-01T11:22:55.013215Z",
"created_at": "2023-12-01T11:22:47.145351Z",
"data_removed": false,
"error": null,
"id": "jgdnwyzby3bobcctcnm5ifo5y4",
"input": {
"protect": 0.33,
"rvc_model": "CUSTOM",
"index_rate": 0.5,
"song_input": "https://replicate.delivery/pbxt/JyMOAadCqhOZxgTZ8ZQUTCERdoh26oGM2nIJP67lSLWGZQnd/silence-lambs-trimmed.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,
"custom_rvc_model_download_url": "https://huggingface.co/CxronaBxndit/Morgan-Freeman/resolve/main/Morgan-Freeman.zip"
},
"logs": "[!] The model will be downloaded as 'Morgan-Freeman'.\n[~] Downloading voice model with name Morgan-Freeman...\nVoice model directory Morgan-Freeman already exists! Skipping download.\n[~] Starting AI Cover Generation Pipeline...\n[~] Converting voice using RVC...\n2023-12-01 11:22:47 | INFO | fairseq.tasks.hubert_pretraining | current directory is /src\n2023-12-01 11:22:47 | INFO | fairseq.tasks.hubert_pretraining | HubertPretrainingTask Config {'_name': 'hubert_pretraining', 'data': 'metadata', 'fine_tuning': False, 'labels': ['km'], 'label_dir': 'label', 'label_rate': 50.0, 'sample_rate': 16000, 'normalize': False, 'enable_padding': False, 'max_keep_size': None, 'max_sample_size': 250000, 'min_sample_size': 32000, 'single_target': False, 'random_crop': True, 'pad_audio': False}\n2023-12-01 11:22:47 | INFO | fairseq.models.hubert.hubert | HubertModel Config: {'_name': 'hubert', 'label_rate': 50.0, 'extractor_mode': default, 'encoder_layers': 12, 'encoder_embed_dim': 768, 'encoder_ffn_embed_dim': 3072, 'encoder_attention_heads': 12, 'activation_fn': gelu, 'layer_type': transformer, 'dropout': 0.1, 'attention_dropout': 0.1, 'activation_dropout': 0.0, 'encoder_layerdrop': 0.05, 'dropout_input': 0.1, 'dropout_features': 0.1, 'final_dim': 256, 'untie_final_proj': True, 'layer_norm_first': False, 'conv_feature_layers': '[(512,10,5)] + [(512,3,2)] * 4 + [(512,2,2)] * 2', 'conv_bias': False, 'logit_temp': 0.1, 'target_glu': False, 'feature_grad_mult': 0.1, 'mask_length': 10, 'mask_prob': 0.8, 'mask_selection': static, 'mask_other': 0.0, 'no_mask_overlap': False, 'mask_min_space': 1, 'mask_channel_length': 10, 'mask_channel_prob': 0.0, 'mask_channel_selection': static, 'mask_channel_other': 0.0, 'no_mask_channel_overlap': False, 'mask_channel_min_space': 1, 'conv_pos': 128, 'conv_pos_groups': 16, 'latent_temp': [2.0, 0.5, 0.999995], 'skip_masked': False, 'skip_nomask': False, 'checkpoint_activations': False, 'required_seq_len_multiple': 2, 'depthwise_conv_kernel_size': 31, 'attn_type': '', 'pos_enc_type': 'abs', 'fp16': False}\ngin_channels: 256 self.spk_embed_dim: 109\n<All keys matched successfully>\n[~] Applying audio effects to Vocals...\n[~] Combining AI Vocals and Instrumentals...\n[~] Removing intermediate audio files...\n[+] Cover generated at /src/song_output/e4c95cc6b96/tmp3klghzvksilence-lambs-trimmed (Morgan-Freeman Ver).mp3",
"metrics": {
"predict_time": 7.850824,
"total_time": 7.867864
},
"output": "https://replicate.delivery/pbxt/ILHNSgdwBeyvVKhbNNflKjKNv1g7Cmk6CAdFGKuW98TOQ39RA/tmp3klghzvksilence-lambs-trimmed%20%28Morgan-Freeman%20Ver%29.mp3",
"started_at": "2023-12-01T11:22:47.162391Z",
"status": "succeeded",
"urls": {
"get": "https://api.replicate.com/v1/predictions/jgdnwyzby3bobcctcnm5ifo5y4",
"cancel": "https://api.replicate.com/v1/predictions/jgdnwyzby3bobcctcnm5ifo5y4/cancel"
},
"version": "0a9c7c558af4c0f20667c1bd1260ce32a2879944a0b9e44e1398660c077b1550"
}Generated in
[!] The model will be downloaded as 'Morgan-Freeman'.
[~] Downloading voice model with name Morgan-Freeman...
Voice model directory Morgan-Freeman already exists! Skipping download.
[~] Starting AI Cover Generation Pipeline...
[~] Converting voice using RVC...
2023-12-01 11:22:47 | INFO | fairseq.tasks.hubert_pretraining | current directory is /src
2023-12-01 11:22:47 | INFO | fairseq.tasks.hubert_pretraining | HubertPretrainingTask Config {'_name': 'hubert_pretraining', 'data': 'metadata', 'fine_tuning': False, 'labels': ['km'], 'label_dir': 'label', 'label_rate': 50.0, 'sample_rate': 16000, 'normalize': False, 'enable_padding': False, 'max_keep_size': None, 'max_sample_size': 250000, 'min_sample_size': 32000, 'single_target': False, 'random_crop': True, 'pad_audio': False}
2023-12-01 11:22:47 | INFO | fairseq.models.hubert.hubert | HubertModel Config: {'_name': 'hubert', 'label_rate': 50.0, 'extractor_mode': default, 'encoder_layers': 12, 'encoder_embed_dim': 768, 'encoder_ffn_embed_dim': 3072, 'encoder_attention_heads': 12, 'activation_fn': gelu, 'layer_type': transformer, 'dropout': 0.1, 'attention_dropout': 0.1, 'activation_dropout': 0.0, 'encoder_layerdrop': 0.05, 'dropout_input': 0.1, 'dropout_features': 0.1, 'final_dim': 256, 'untie_final_proj': True, 'layer_norm_first': False, 'conv_feature_layers': '[(512,10,5)] + [(512,3,2)] * 4 + [(512,2,2)] * 2', 'conv_bias': False, 'logit_temp': 0.1, 'target_glu': False, 'feature_grad_mult': 0.1, 'mask_length': 10, 'mask_prob': 0.8, 'mask_selection': static, 'mask_other': 0.0, 'no_mask_overlap': False, 'mask_min_space': 1, 'mask_channel_length': 10, 'mask_channel_prob': 0.0, 'mask_channel_selection': static, 'mask_channel_other': 0.0, 'no_mask_channel_overlap': False, 'mask_channel_min_space': 1, 'conv_pos': 128, 'conv_pos_groups': 16, 'latent_temp': [2.0, 0.5, 0.999995], 'skip_masked': False, 'skip_nomask': False, 'checkpoint_activations': False, 'required_seq_len_multiple': 2, 'depthwise_conv_kernel_size': 31, 'attn_type': '', 'pos_enc_type': 'abs', 'fp16': False}
gin_channels: 256 self.spk_embed_dim: 109
<All keys matched successfully>
[~] Applying audio effects to Vocals...
[~] Combining AI Vocals and Instrumentals...
[~] Removing intermediate audio files...
[+] Cover generated at /src/song_output/e4c95cc6b96/tmp3klghzvksilence-lambs-trimmed (Morgan-Freeman Ver).mp3