zsxkib
/
realistic-voice-cloning
Create song covers with any RVC v2 trained AI voice from audio files.
Prediction
zsxkib/realistic-voice-cloning:0a9c7c55Input
- protect
- 0.5
- rvc_model
- CUSTOM
- index_rate
- 1
- song_input
- Video Player is loading.Current Time 00:00:000/Duration 00:00:000Loaded: 0%Stream 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
- 0.6
- pitch_change
- female-to-male
- rms_mix_rate
- 0.8
- filter_radius
- 3
- output_format
- mp3
- reverb_damping
- 0.7
- reverb_dryness
- 0.8
- reverb_wetness
- 0.3
- crepe_hop_length
- 8
- pitch_change_all
- 0
- main_vocals_volume_change
- 3
- pitch_detection_algorithm
- mangio-crepe
- instrumental_volume_change
- 0
- backup_vocals_volume_change
- -10
- custom_rvc_model_download_url
- https://weights.replicate.delivery/default/rvc/SamA.zip
{ "protect": 0.5, "rvc_model": "CUSTOM", "index_rate": 1, "song_input": "https://replicate.delivery/pbxt/JvgakOpSJzQRSNYymHq2gKmQws48cye3DlCSL55qxu9f5YQt/taylor-trim.mp3", "reverb_size": 0.6, "pitch_change": "female-to-male", "rms_mix_rate": 0.8, "filter_radius": 3, "output_format": "mp3", "reverb_damping": 0.7, "reverb_dryness": 0.8, "reverb_wetness": 0.3, "crepe_hop_length": 8, "pitch_change_all": 0, "main_vocals_volume_change": 3, "pitch_detection_algorithm": "mangio-crepe", "instrumental_volume_change": 0, "backup_vocals_volume_change": -10, "custom_rvc_model_download_url": "https://weights.replicate.delivery/default/rvc/SamA.zip" }
Install Replicate’s Node.js client library:npm install replicate
Set theREPLICATE_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: 0.5, rvc_model: "CUSTOM", index_rate: 1, song_input: "https://replicate.delivery/pbxt/JvgakOpSJzQRSNYymHq2gKmQws48cye3DlCSL55qxu9f5YQt/taylor-trim.mp3", reverb_size: 0.6, pitch_change: "female-to-male", rms_mix_rate: 0.8, filter_radius: 3, output_format: "mp3", reverb_damping: 0.7, reverb_dryness: 0.8, reverb_wetness: 0.3, crepe_hop_length: 8, pitch_change_all: 0, main_vocals_volume_change: 3, pitch_detection_algorithm: "mangio-crepe", instrumental_volume_change: 0, backup_vocals_volume_change: -10, custom_rvc_model_download_url: "https://weights.replicate.delivery/default/rvc/SamA.zip" } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the client:import replicate
Run 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": 0.5, "rvc_model": "CUSTOM", "index_rate": 1, "song_input": "https://replicate.delivery/pbxt/JvgakOpSJzQRSNYymHq2gKmQws48cye3DlCSL55qxu9f5YQt/taylor-trim.mp3", "reverb_size": 0.6, "pitch_change": "female-to-male", "rms_mix_rate": 0.8, "filter_radius": 3, "output_format": "mp3", "reverb_damping": 0.7, "reverb_dryness": 0.8, "reverb_wetness": 0.3, "crepe_hop_length": 8, "pitch_change_all": 0, "main_vocals_volume_change": 3, "pitch_detection_algorithm": "mangio-crepe", "instrumental_volume_change": 0, "backup_vocals_volume_change": -10, "custom_rvc_model_download_url": "https://weights.replicate.delivery/default/rvc/SamA.zip" } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_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": 0.5, "rvc_model": "CUSTOM", "index_rate": 1, "song_input": "https://replicate.delivery/pbxt/JvgakOpSJzQRSNYymHq2gKmQws48cye3DlCSL55qxu9f5YQt/taylor-trim.mp3", "reverb_size": 0.6, "pitch_change": "female-to-male", "rms_mix_rate": 0.8, "filter_radius": 3, "output_format": "mp3", "reverb_damping": 0.7, "reverb_dryness": 0.8, "reverb_wetness": 0.3, "crepe_hop_length": 8, "pitch_change_all": 0, "main_vocals_volume_change": 3, "pitch_detection_algorithm": "mangio-crepe", "instrumental_volume_change": 0, "backup_vocals_volume_change": -10, "custom_rvc_model_download_url": "https://weights.replicate.delivery/default/rvc/SamA.zip" } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
Video Player is loading.Current Time 00:00:000/Duration 00:00:000Loaded: 0%Stream 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.
{ "completed_at": "2023-11-23T22:35:46.750107Z", "created_at": "2023-11-23T22:34:13.064309Z", "data_removed": false, "error": null, "id": "imxvh7jbwwvell3fwpcpxommlm", "input": { "protect": 0.5, "rvc_model": "CUSTOM", "index_rate": 1, "song_input": "https://replicate.delivery/pbxt/JvgakOpSJzQRSNYymHq2gKmQws48cye3DlCSL55qxu9f5YQt/taylor-trim.mp3", "reverb_size": 0.6, "pitch_change": "female-to-male", "rms_mix_rate": 0.8, "filter_radius": 3, "output_format": "mp3", "reverb_damping": 0.7, "reverb_dryness": 0.8, "reverb_wetness": 0.3, "crepe_hop_length": 8, "pitch_change_all": 0, "main_vocals_volume_change": 3, "pitch_detection_algorithm": "mangio-crepe", "instrumental_volume_change": 0, "backup_vocals_volume_change": -10, "custom_rvc_model_download_url": "https://weights.replicate.delivery/default/rvc/SamA.zip" }, "logs": "[!] The model will be downloaded as 'SamA'.\n[~] Downloading voice model with name SamA...\nVoice model directory SamA already exists! Skipping download.\n[~] Starting AI Cover Generation Pipeline...\n[~] Converting voice using RVC...\n2023-11-23 22:34:13 | INFO | fairseq.tasks.hubert_pretraining | current directory is /src\n2023-11-23 22:34:13 | 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}\n2023-11-23 22:34:13 | 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>\nInitiating prediction with a crepe_hop_length of: 8\n[~] Applying audio effects to Vocals...\n[~] Combining AI Vocals and Instrumentals...\n[~] Removing intermediate audio files...\n[+] Cover generated at /src/song_output/ba478873b07/tmp4rkutngetaylor-trim (SamA Ver).mp3", "metrics": { "predict_time": 93.672594, "total_time": 93.685798 }, "output": "https://replicate.delivery/pbxt/MdNcQoik3A6NCFYm2JWtQIkPVeqRdusuDf7Bok2VvxICXY7RA/tmp4rkutngetaylor-trim%20%28SamA%20Ver%29.mp3", "started_at": "2023-11-23T22:34:13.077513Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/imxvh7jbwwvell3fwpcpxommlm", "cancel": "https://api.replicate.com/v1/predictions/imxvh7jbwwvell3fwpcpxommlm/cancel" }, "version": "0a9c7c558af4c0f20667c1bd1260ce32a2879944a0b9e44e1398660c077b1550" }
Generated in[!] The model will be downloaded as 'SamA'. [~] Downloading voice model with name SamA... Voice model directory SamA already exists! Skipping download. [~] Starting AI Cover Generation Pipeline... [~] Converting voice using RVC... 2023-11-23 22:34:13 | INFO | fairseq.tasks.hubert_pretraining | current directory is /src 2023-11-23 22:34:13 | 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} 2023-11-23 22:34:13 | 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> Initiating prediction with a crepe_hop_length of: 8 [~] Applying audio effects to Vocals... [~] Combining AI Vocals and Instrumentals... [~] Removing intermediate audio files... [+] Cover generated at /src/song_output/ba478873b07/tmp4rkutngetaylor-trim (SamA Ver).mp3
Prediction
zsxkib/realistic-voice-cloning:0a9c7c55IDopfbdorbymurmp2ykemgwe23qaStatusSucceededSourceWebHardwareT4Total durationCreatedInput
- protect
- 0.33
- rvc_model
- Squidward
- index_rate
- 0.5
- song_input
- Video Player is loading.Current Time 00:00:000/Duration 00:00:000Loaded: 0%Stream 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
{ "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 }
Install Replicate’s Node.js client library:npm install replicate
Set theREPLICATE_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: "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 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the client:import replicate
Run 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": "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 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_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": "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 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
Video Player is loading.Current Time 00:00:000/Duration 00:00:000Loaded: 0%Stream 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.
{ "completed_at": "2023-11-14T16:52:22.833233Z", "created_at": "2023-11-14T16:52:20.000859Z", "data_removed": false, "error": null, "id": "opfbdorbymurmp2ykemgwe23qa", "input": { "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 }, "logs": "[~] Starting AI Cover Generation Pipeline...\n[~] Applying audio effects to Vocals...\n[~] Combining AI Vocals and Instrumentals...\n[~] Removing intermediate audio files...\n[+] Cover generated at /src/song_output/d0386572142/tmp11cudxj_gangnam (Squidward Ver).mp3", "metrics": { "predict_time": 2.811273, "total_time": 2.832374 }, "output": "https://replicate.delivery/pbxt/TqYjsueAmlVePUapV0rf7MCDCDBfAJxhw2aE5euzA6Gw4rCPC/tmp11cudxj_gangnam%20%28Squidward%20Ver%29.mp3", "started_at": "2023-11-14T16:52:20.021960Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/opfbdorbymurmp2ykemgwe23qa", "cancel": "https://api.replicate.com/v1/predictions/opfbdorbymurmp2ykemgwe23qa/cancel" }, "version": "a0076ea13a704d9fa6d02535bc8951d3b141c84dc95d2d3f2f5016eabfcb8d94" }
Generated in[~] 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
Prediction
zsxkib/realistic-voice-cloning:0a9c7c55Input
- protect
- 0.33
- rvc_model
- Drake
- index_rate
- 0.5
- song_input
- Video Player is loading.Current Time 00:00:000/Duration 00:00:000Loaded: 0%Stream 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/QuickWick/Music-AI-Voices/resolve/main/Drake%20(RVC)%20Unknown%20Steps/Drake%20(RVC)%20Unknown.zip?download=true
- custom_rvc_model_download_name
- Drake
{ "protect": 0.33, "rvc_model": "Drake", "index_rate": 0.5, "song_input": "https://replicate.delivery/pbxt/JsPKaofgQCRLKdATUj55amn131wSNMTl3pYYbJ7oUNAR2cV3/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, "custom_rvc_model_download_url": "https://huggingface.co/QuickWick/Music-AI-Voices/resolve/main/Drake%20(RVC)%20Unknown%20Steps/Drake%20(RVC)%20Unknown.zip?download=true", "custom_rvc_model_download_name": "Drake" }
Install Replicate’s Node.js client library:npm install replicate
Set theREPLICATE_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: "Drake", index_rate: 0.5, song_input: "https://replicate.delivery/pbxt/JsPKaofgQCRLKdATUj55amn131wSNMTl3pYYbJ7oUNAR2cV3/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, custom_rvc_model_download_url: "https://huggingface.co/QuickWick/Music-AI-Voices/resolve/main/Drake%20(RVC)%20Unknown%20Steps/Drake%20(RVC)%20Unknown.zip?download=true" } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the client:import replicate
Run 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": "Drake", "index_rate": 0.5, "song_input": "https://replicate.delivery/pbxt/JsPKaofgQCRLKdATUj55amn131wSNMTl3pYYbJ7oUNAR2cV3/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, "custom_rvc_model_download_url": "https://huggingface.co/QuickWick/Music-AI-Voices/resolve/main/Drake%20(RVC)%20Unknown%20Steps/Drake%20(RVC)%20Unknown.zip?download=true" } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_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": "Drake", "index_rate": 0.5, "song_input": "https://replicate.delivery/pbxt/JsPKaofgQCRLKdATUj55amn131wSNMTl3pYYbJ7oUNAR2cV3/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, "custom_rvc_model_download_url": "https://huggingface.co/QuickWick/Music-AI-Voices/resolve/main/Drake%20(RVC)%20Unknown%20Steps/Drake%20(RVC)%20Unknown.zip?download=true" } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
Video Player is loading.Current Time 00:00:000/Duration 00:00:000Loaded: 0%Stream 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.
{ "completed_at": "2023-11-14T16:54:32.313003Z", "created_at": "2023-11-14T16:54:17.086359Z", "data_removed": false, "error": null, "id": "czmmyuzbky3fcexrpa4wtj5xtm", "input": { "protect": 0.33, "rvc_model": "Drake", "index_rate": 0.5, "song_input": "https://replicate.delivery/pbxt/JsPKaofgQCRLKdATUj55amn131wSNMTl3pYYbJ7oUNAR2cV3/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, "custom_rvc_model_download_url": "https://huggingface.co/QuickWick/Music-AI-Voices/resolve/main/Drake%20(RVC)%20Unknown%20Steps/Drake%20(RVC)%20Unknown.zip?download=true", "custom_rvc_model_download_name": "Drake" }, "logs": "[!] The model will be downloaded as 'Drake'. To use it, you'll need to match it on 'rvc_model'.\n[~] Downloading voice model with name Drake...\n[~] Extracting zip...\n[+] Drake Model successfully downloaded!\n[~] Starting AI Cover Generation Pipeline...\n[~] Converting voice using RVC...\n2023-11-14 16:54:22 | INFO | fairseq.tasks.hubert_pretraining | current directory is /src\n2023-11-14 16:54:22 | 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}\n2023-11-14 16:54:22 | 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/d0386572142/tmp11cudxj_gangnam (Drake Ver).mp3", "metrics": { "predict_time": 15.203292, "total_time": 15.226644 }, "output": "https://replicate.delivery/pbxt/lLemP3Q7Wm3wJSe1LYUGwO4U9sJgsuTx9b8SsbyCUwkHhV4RA/tmp11cudxj_gangnam%20%28Drake%20Ver%29.mp3", "started_at": "2023-11-14T16:54:17.109711Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/czmmyuzbky3fcexrpa4wtj5xtm", "cancel": "https://api.replicate.com/v1/predictions/czmmyuzbky3fcexrpa4wtj5xtm/cancel" }, "version": "a0076ea13a704d9fa6d02535bc8951d3b141c84dc95d2d3f2f5016eabfcb8d94" }
Generated in[!] The model will be downloaded as 'Drake'. To use it, you'll need to match it on 'rvc_model'. [~] Downloading voice model with name Drake... [~] Extracting zip... [+] Drake Model successfully downloaded! [~] Starting AI Cover Generation Pipeline... [~] Converting voice using RVC... 2023-11-14 16:54:22 | INFO | fairseq.tasks.hubert_pretraining | current directory is /src 2023-11-14 16:54:22 | 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} 2023-11-14 16:54:22 | 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/d0386572142/tmp11cudxj_gangnam (Drake Ver).mp3
Prediction
zsxkib/realistic-voice-cloning:0a9c7c55Input
- protect
- 0.33
- rvc_model
- Trump
- index_rate
- 0.5
- song_input
- Video Player is loading.Current Time 00:00:000/Duration 00:00:000Loaded: 0%Stream 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
- 3
- pitch_detection_algorithm
- rmvpe
- instrumental_volume_change
- 0
- backup_vocals_volume_change
- 0
- custom_rvc_model_download_url
- https://huggingface.co/0x3e9/0x3e9_RVC_models/resolve/main/trump.zip
- custom_rvc_model_download_name
- Trump
{ "protect": 0.33, "rvc_model": "Trump", "index_rate": 0.5, "song_input": "https://replicate.delivery/pbxt/JsPlGg4HNPYrcOqxDfu3ANm1pK5JntJgVwg30Yd8cV9jBVFN/number-15-burger-king-foot-lettuce.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": 3, "pitch_detection_algorithm": "rmvpe", "instrumental_volume_change": 0, "backup_vocals_volume_change": 0, "custom_rvc_model_download_url": "https://huggingface.co/0x3e9/0x3e9_RVC_models/resolve/main/trump.zip", "custom_rvc_model_download_name": "Trump" }
Install Replicate’s Node.js client library:npm install replicate
Set theREPLICATE_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: "Trump", index_rate: 0.5, song_input: "https://replicate.delivery/pbxt/JsPlGg4HNPYrcOqxDfu3ANm1pK5JntJgVwg30Yd8cV9jBVFN/number-15-burger-king-foot-lettuce.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: 3, pitch_detection_algorithm: "rmvpe", instrumental_volume_change: 0, backup_vocals_volume_change: 0, custom_rvc_model_download_url: "https://huggingface.co/0x3e9/0x3e9_RVC_models/resolve/main/trump.zip" } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Set theREPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the client:import replicate
Run 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": "Trump", "index_rate": 0.5, "song_input": "https://replicate.delivery/pbxt/JsPlGg4HNPYrcOqxDfu3ANm1pK5JntJgVwg30Yd8cV9jBVFN/number-15-burger-king-foot-lettuce.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": 3, "pitch_detection_algorithm": "rmvpe", "instrumental_volume_change": 0, "backup_vocals_volume_change": 0, "custom_rvc_model_download_url": "https://huggingface.co/0x3e9/0x3e9_RVC_models/resolve/main/trump.zip" } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_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": "Trump", "index_rate": 0.5, "song_input": "https://replicate.delivery/pbxt/JsPlGg4HNPYrcOqxDfu3ANm1pK5JntJgVwg30Yd8cV9jBVFN/number-15-burger-king-foot-lettuce.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": 3, "pitch_detection_algorithm": "rmvpe", "instrumental_volume_change": 0, "backup_vocals_volume_change": 0, "custom_rvc_model_download_url": "https://huggingface.co/0x3e9/0x3e9_RVC_models/resolve/main/trump.zip" } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
Video Player is loading.Current Time 00:00:000/Duration 00:00:000Loaded: 0%Stream 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.
{ "completed_at": "2023-11-14T17:22:28.282817Z", "created_at": "2023-11-14T17:22:26.382065Z", "data_removed": false, "error": null, "id": "2pz4qhjbss3u2wghs4ply4ddxq", "input": { "protect": 0.33, "rvc_model": "Trump", "index_rate": 0.5, "song_input": "https://replicate.delivery/pbxt/JsPlGg4HNPYrcOqxDfu3ANm1pK5JntJgVwg30Yd8cV9jBVFN/number-15-burger-king-foot-lettuce.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": 3, "pitch_detection_algorithm": "rmvpe", "instrumental_volume_change": 0, "backup_vocals_volume_change": 0, "custom_rvc_model_download_url": "https://huggingface.co/0x3e9/0x3e9_RVC_models/resolve/main/trump.zip", "custom_rvc_model_download_name": "Trump" }, "logs": "[!] The model will be downloaded as 'Trump'. To use it, you'll need to match it on 'rvc_model'.\n[~] Downloading voice model with name Trump...\nVoice model directory Trump already exists! Skipping download.\n[~] Starting AI Cover Generation Pipeline...\n[~] Applying audio effects to Vocals...\n[~] Combining AI Vocals and Instrumentals...\n[~] Removing intermediate audio files...\n[+] Cover generated at /src/song_output/897478c94e0/tmp_t9sx107number-15-burger-king-foot-lettuce (Trump Ver).mp3", "metrics": { "predict_time": 1.879513, "total_time": 1.900752 }, "output": "https://replicate.delivery/pbxt/AgbkhkuFvZokJNtwoQLAcgeOCcWYCtBBeVJNyw0vLRfo2rwjA/tmp_t9sx107number-15-burger-king-foot-lettuce%20%28Trump%20Ver%29.mp3", "started_at": "2023-11-14T17:22:26.403304Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/2pz4qhjbss3u2wghs4ply4ddxq", "cancel": "https://api.replicate.com/v1/predictions/2pz4qhjbss3u2wghs4ply4ddxq/cancel" }, "version": "a0076ea13a704d9fa6d02535bc8951d3b141c84dc95d2d3f2f5016eabfcb8d94" }
Generated in[!] The model will be downloaded as 'Trump'. To use it, you'll need to match it on 'rvc_model'. [~] Downloading voice model with name Trump... Voice model directory Trump already exists! Skipping download. [~] 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/897478c94e0/tmp_t9sx107number-15-burger-king-foot-lettuce (Trump Ver).mp3
Want to make some of these yourself?
Run this model